© 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. 14049
    Prev
    Next
    INDEX
    Explanations

    mentions of specific goals or aspirations within text

    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
    247
    +0.18
    0.6%
    679
    +0.17
    0.6%
    288
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    247
    +0.18
    0.07
    690
    +0.17
    0.04
    509
    +0.15
    0.04
    Negative Logits
    oute
    -1.05
    ols
    -0.93
    ork
    -0.89
    Python
    -0.89
    orks
    -0.88
    Luck
    -0.86
     Solitaire
    -0.86
    oles
    -0.85
    urrency
    -0.85
    cling
    -0.85
    POSITIVE LOGITS
    posts
    1.31
    Goal
    1.05
    goal
    1.03
     accomplished
    1.03
    eers
    1.02
     Goal
    1.02
     goal
    0.97
    ims
    0.96
    lessly
    0.93
     scorer
    0.92
    Activations Density 0.817%

    No Known Activations