© 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
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 39660
    Prev
    Next
    INDEX
    Explanations

    companies, funding, and business-related terms

    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
    +0.18
    0.8%
    288
    +0.14
    0.7%
    195
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.18
    0.21
    151
    +0.14
    0.16
    762
    +0.14
    0.14
    Negative Logits
    mith
    -0.72
    */(
    -0.66
    ãħĭ
    -0.65
    urgy
    -0.64
     reconc
    -0.64
    ivari
    -0.64
    arling
    -0.64
    aver
    -0.63
    ĪĴ
    -0.63
    eus
    -0.63
    POSITIVE LOGITS
     capitalists
    0.87
     venture
    0.85
     capitalist
    0.82
    ONSORED
    0.76
     ventures
    0.76
    iously
    0.69
    XT
    0.66
    TAIN
    0.66
    ty
    0.64
    bilt
    0.63
    Activations Density 6.460%

    No Known Activations