© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 36833
    Prev
    Next
    INDEX
    Explanations

    words related to different worlds or environments

    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
    +0.22
    1.1%
    203
    +0.10
    0.5%
    527
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    323
    +0.22
    0.09
    535
    +0.10
    0.04
    203
    +0.08
    0.07
    Negative Logits
    ippi
    -0.78
     actionGroup
    -0.76
    odox
    -0.73
    icer
    -0.69
    indal
    -0.68
    oug
    -0.68
    etsk
    -0.67
    ipop
    -0.64
    ibility
    -0.64
    ratulations
    -0.63
    POSITIVE LOGITS
    building
    0.90
    liness
    0.78
    scape
    0.76
     Reincarn
    0.72
    wide
    0.65
    views
    0.64
    fare
    0.61
    icz
    0.61
    spawn
    0.61
    arium
    0.60
    Activations Density 8.190%

    No Known Activations