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

    Neuronpedia

    Jacobian LensNEW
    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. 12659
    Prev
    Next
    INDEX
    Explanations

    mentions of legal cases, criminal activities, and law enforcement actions

    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
    154
    +0.04
    0.5%
    429
    +0.04
    0.4%
    701
    +0.03
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.04
    -0.01
    582
    +0.04
    0.01
    563
    +0.03
    0.01
    Negative Logits
     Mub
    -0.25
     Kills
    -0.25
     duck
    -0.24
    tein
    -0.23
     pretending
    -0.23
     wastes
    -0.22
     whirlwind
    -0.22
     Transcript
    -0.22
    isbury
    -0.22
    ustain
    -0.21
    POSITIVE LOGITS
    wid
    0.29
    oké
    0.26
    rose
    0.25
    aid
    0.25
    river
    0.25
    onite
    0.24
     protector
    0.24
    riz
    0.24
    runner
    0.23
     âĶľ
    0.23
    Activations Density 0.021%

    No Known Activations