© 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
    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. 1928
    Prev
    Next
    INDEX
    Explanations

    information related to legal rulings and judgments

    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
    159
    +0.11
    0.6%
    357
    +0.10
    0.6%
    221
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    357
    +0.11
    0.02
    18
    +0.10
    0.02
    288
    +0.09
    0.02
    Negative Logits
     Beet
    -0.62
    çļ
    -0.60
     Maiden
    -0.59
     Juda
    -0.57
     eleph
    -0.57
     Remain
    -0.55
    roy
    -0.54
     Syd
    -0.52
    ISA
    -0.52
     repay
    -0.52
    POSITIVE LOGITS
    eret
    0.64
    cation
    0.57
     [+]
    0.56
    "]
    0.56
    CVE
    0.54
    purpose
    0.54
    iqu
    0.53
     edit
    0.53
    UGH
    0.53
    addons
    0.53
    Activations Density 0.069%

    No Known Activations