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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 5390
    Prev
    Next
    INDEX
    Explanations

    phrases related to political campaigning and activism

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    445
    +0.15
    0.5%
    514
    +0.15
    0.5%
    131
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    49
    +0.15
    0.08
    566
    +0.15
    0.07
    718
    +0.14
    0.07
    Negative Logits
    DAQ
    -0.91
     Witches
    -0.91
    rique
    -0.89
     Complex
    -0.88
    ibaba
    -0.88
    blem
    -0.88
    infeld
    -0.88
    IVER
    -0.87
     Dys
    -0.87
    EStreamFrame
    -0.87
    POSITIVE LOGITS
     behold
    0.96
     forgive
    0.96
     grap
    0.95
     obedient
    0.94
     grant
    0.94
     kindly
    0.93
     pardon
    0.92
     goof
    0.90
    ogle
    0.90
     boot
    0.90
    Activations Density 0.996%

    No Known Activations