© 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. 12990
    Prev
    Next
    INDEX
    Explanations

    details related to theft, robbery, and criminal activities

    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
    +0.13
    0.5%
    366
    +0.13
    0.5%
    35
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.12
    326
    +0.13
    0.09
    32
    +0.13
    0.07
    Negative Logits
    ffen
    -0.82
    Reviewer
    -0.80
    live
    -0.78
    eele
    -0.76
    br
    -0.74
    bsp
    -0.72
    aired
    -0.71
    eq
    -0.71
    mite
    -0.70
     Divinity
    -0.70
    POSITIVE LOGITS
     spree
    1.18
     robbery
    1.06
     synd
    0.98
     robberies
    0.97
     scams
    0.94
     extortion
    0.92
    ster
    0.92
    sters
    0.92
     gangs
    0.91
    eering
    0.90
    Activations Density 1.449%

    No Known Activations