© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 39470
    Prev
    Next
    INDEX
    Explanations

    words related to socio-economic disparities, including terms related to income, assistance programs, and healthcare accessibility

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.28
    1.4%
    536
    +0.09
    0.4%
    592
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    660
    +0.28
    0.12
    600
    +0.09
    0.11
    669
    +0.08
    0.10
    Negative Logits
    ĸļ
    -0.78
     Canaver
    -0.73
    antine
    -0.69
    ãĥķãĤ©
    -0.67
     tremend
    -0.67
     Definitive
    -0.65
    asso
    -0.65
     conclud
    -0.63
    arium
    -0.63
    ILA
    -0.62
    POSITIVE LOGITS
     individuals
    1.22
     persons
    1.19
     youths
    1.14
     households
    1.14
     retirees
    1.05
     families
    1.05
     Britons
    1.03
     peoples
    1.00
     people
    1.00
     earners
    0.97
    Activations Density 16.846%

    No Known Activations