© 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. 34930
    Prev
    Next
    INDEX
    Explanations

    text relating to current social and political issues, particularly concerning controversial figures and topics

    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
    498
    +0.14
    0.5%
    447
    +0.13
    0.5%
    106
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    267
    +0.14
    0.14
    582
    +0.13
    0.10
    2
    +0.12
    0.08
    Negative Logits
    existent
    -0.81
    senal
    -0.80
    pora
    -0.76
    luster
    -0.73
     Prelude
    -0.72
    externalActionCode
    -0.72
    glomer
    -0.70
     conflic
    -0.69
     pupil
    -0.69
    der
    -0.69
    POSITIVE LOGITS
    ifications
    1.35
    ices
    1.30
     kidding
    1.28
    ifiable
    1.21
    itia
    1.13
    icia
    1.13
    ification
    1.12
    ifi
    1.11
    if
    1.10
    ified
    1.07
    Activations Density 7.670%

    No Known Activations