© 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. 31430
    Prev
    Next
    INDEX
    Explanations

    words related to the tongue or speech

    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
    339
    +0.11
    0.6%
    352
    +0.10
    0.5%
    236
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.11
    0.20
    288
    +0.10
    0.19
    659
    +0.09
    0.08
    Negative Logits
    eanor
    -0.81
    negie
    -0.78
    illon
    -0.73
    ashtra
    -0.69
    eus
    -0.68
    agna
    -0.67
    ilion
    -0.67
    iary
    -0.67
    ean
    -0.67
    igans
    -0.67
    POSITIVE LOGITS
    warm
    0.71
     depress
    0.67
    cker
    0.65
    gently
    0.65
    cean
    0.63
    que
    0.63
    #$
    0.63
    lette
    0.61
    waters
    0.60
    Äĩ
    0.60
    Activations Density 6.728%

    No Known Activations