© 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. 1265
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal or criminal activities

    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
    447
    +0.18
    0.7%
    288
    +0.14
    0.5%
    603
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.18
    0.18
    346
    +0.14
    0.11
    91
    +0.12
    0.11
    Negative Logits
    aber
    -0.86
    Translation
    -0.86
    æĹ
    -0.86
    âĹ¼
    -0.84
    ankind
    -0.80
    aeda
    -0.80
    usters
    -0.79
    âĶĢâĶĢâĶĢâĶĢ
    -0.79
     nostalg
    -0.79
    ãĢĤ
    -0.79
    POSITIVE LOGITS
     jailed
    1.06
     accused
    1.03
     convicted
    1.01
     sentenced
    1.00
     fatally
    0.96
     pleaded
    0.96
     gunman
    0.94
     gunned
    0.94
     wrongly
    0.92
     arrested
    0.92
    Activations Density 4.136%

    No Known Activations