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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 5871
    Prev
    Next
    INDEX
    Explanations

    mentions of possession, especially related to drugs like marijuana

    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
    +0.17
    0.8%
    271
    +0.16
    0.7%
    343
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    761
    +0.17
    0.05
    271
    +0.16
    0.04
    332
    +0.13
    0.06
    Negative Logits
    mitt
    -0.84
    gnu
    -0.77
    htt
    -0.73
    MQ
    -0.72
    bank
    -0.72
    HCR
    -0.70
    κ
    -0.68
     externalToEVAOnly
    -0.68
    mys
    -0.67
    RFC
    -0.66
    POSITIVE LOGITS
    ership
    1.03
    ively
    0.99
    ivity
    0.98
    ive
    0.97
    iveness
    0.96
     possession
    0.95
    IVE
    0.93
    ibility
    0.90
    iture
    0.89
    orial
    0.88
    Activations Density 1.320%

    No Known Activations