© 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. 33888
    Prev
    Next
    INDEX
    Explanations

    words related to public figures and political scandals

    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
    1.5%
    353
    +0.05
    0.4%
    401
    +0.05
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.18
    0.37
    41
    +0.05
    0.11
    401
    +0.05
    0.18
    Negative Logits
     although
    -0.28
     Hels
    -0.28
    !.
    -0.27
     Pearce
    -0.27
     ASAP
    -0.27
    iverpool
    -0.27
     Kak
    -0.27
     Beir
    -0.27
    outube
    -0.27
     tonight
    -0.26
    POSITIVE LOGITS
     persists
    0.39
    pires
    0.39
     becomes
    0.39
     behaves
    0.39
     disappears
    0.39
     has
    0.39
     cannot
    0.38
     loses
    0.37
     seemed
    0.37
     retains
    0.37
    Activations Density 28.497%

    No Known Activations