© 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. 6443
    Prev
    Next
    INDEX
    Explanations

    terms related to law enforcement activities, such as raids and investigations

    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
    326
    +0.18
    0.6%
    269
    +0.15
    0.6%
    464
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.18
    0.07
    288
    +0.15
    0.09
    651
    +0.12
    0.04
    Negative Logits
    DonaldTrump
    -0.98
    clip
    -0.98
     Lauder
    -0.94
    éĸ
    -0.84
     Bie
    -0.82
     Gork
    -0.81
     Ivanka
    -0.80
    PRES
    -0.78
    FUL
    -0.78
     Leilan
    -0.78
    POSITIVE LOGITS
    naires
    1.03
     raiding
    1.03
    veyard
    1.00
    yssey
    0.99
    eta
    0.98
     raid
    0.96
    ers
    0.95
    raid
    0.95
    thouse
    0.93
    hest
    0.91
    Activations Density 0.826%

    No Known Activations