© 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. 5520
    Prev
    Next
    INDEX
    Explanations

    words related to personal stories, behaviors, and personal attributes

    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
    288
    +0.20
    0.8%
    91
    +0.13
    0.5%
    130
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    91
    +0.20
    0.12
    288
    +0.13
    0.13
    575
    +0.12
    0.11
    Negative Logits
     embassies
    -0.87
    crew
    -0.84
    Patch
    -0.73
    WAR
    -0.71
     departments
    -0.70
    ppings
    -0.70
    uld
    -0.69
    events
    -0.69
    Xi
    -0.69
    irs
    -0.69
    POSITIVE LOGITS
     extraord
    1.24
     specializing
    0.97
    ess
    0.93
    ometer
    0.88
    Joined
    0.83
    esses
    0.81
    izer
    0.80
    agonist
    0.78
    digy
    0.75
     whose
    0.74
    Activations Density 1.497%

    No Known Activations