© 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. 31443
    Prev
    Next
    INDEX
    Explanations

    locations where people gather or spend time together

    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
    +0.11
    0.5%
    467
    +0.10
    0.5%
    196
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    437
    +0.11
    0.06
    338
    +0.10
    0.10
    708
    +0.09
    0.07
    Negative Logits
    Ĥİ
    -0.81
    ²¾
    -0.80
    qua
    -0.75
    Ħ¢
    -0.71
    ¿
    -0.70
    ovi
    -0.70
    taboola
    -0.67
    ĨĴ
    -0.67
    ¶ħ
    -0.66
    Ĵ
    -0.66
    POSITIVE LOGITS
     fences
    0.63
     cliffs
    0.62
     Anch
    0.61
     Medals
    0.61
     hang
    0.59
     Hover
    0.59
     trophies
    0.58
     poker
    0.58
     compr
    0.58
     hangs
    0.58
    Activations Density 12.510%

    No Known Activations