© 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 EvalsExportsinterp-engineNEWAPI 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 Local
    9. 6-RES_SCL-AJT
    11. 35849
    Prev
    Next
    INDEX
    Explanations

    references to criminal activities, investigations, and legal proceedings

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    +0.16
    1.2%
    685
    +0.07
    0.5%
    285
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    551
    +0.16
    0.09
    160
    +0.07
    0.20
    141
    +0.07
    0.07
    Negative Logits
    quickShipAvailable
    -0.56
    alg
    -0.50
    orph
    -0.44
    UNCH
    -0.39
     Boards
    -0.38
     Racer
    -0.38
    irl
    -0.38
     RC
    -0.38
    NetMessage
    -0.37
    rik
    -0.37
    POSITIVE LOGITS
     committed
    0.70
     perpetrated
    0.64
     punishable
    0.58
     atrocities
    0.53
     deeds
    0.53
     crimes
    0.51
     against
    0.51
     dishon
    0.49
     involving
    0.47
     abuses
    0.47
    Activations Density 14.520%

    No Known Activations