© 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. 89
    Prev
    Next
    INDEX
    Explanations

    words related to political and social issues

    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
    68
    +0.11
    0.5%
    514
    +0.11
    0.5%
    308
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    154
    +0.11
    0.22
    23
    +0.11
    0.21
    514
    +0.10
    0.18
    Negative Logits
     Palest
    -0.79
    çĶ°
    -0.76
    ãĤ¨ãĥ«
    -0.72
    è£ħ
    -0.71
     guiActiveUnfocused
    -0.71
    osate
    -0.71
     Naz
    -0.69
    ãĤ´
    -0.68
     malnutrition
    -0.67
    Buyable
    -0.67
    POSITIVE LOGITS
    should
    1.03
    £
    0.89
    ¢
    0.87
    sure
    0.86
    âĢķ
    0.84
    might
    0.83
    could
    0.82
    alone
    0.80
    ked
    0.79
    certain
    0.79
    Activations Density 1.120%

    No Known Activations