© 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. 36950
    Prev
    Next
    INDEX
    Explanations

    words related to plants and medical procedures, particularly vaccination

    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
    Neuron Alignment
    Index
    Value
    % of L₁
    595
    +0.10
    0.6%
    319
    +0.09
    0.6%
    99
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.10
    0.23
    326
    +0.09
    0.22
    99
    +0.07
    0.10
    Negative Logits
    bie
    -0.60
     undone
    -0.55
    arov
    -0.55
    ed
    -0.53
    ington
    -0.50
    bies
    -0.50
    eries
    -0.48
    et
    -0.47
    fare
    -0.46
    bourg
    -0.46
    POSITIVE LOGITS
     acid
    0.52
    oxin
    0.51
    milo
    0.50
    ysis
    0.50
    encies
    0.49
    jured
    0.48
    jen
    0.48
    ONSORED
    0.47
     cooker
    0.47
     ox
    0.47
    Activations Density 8.027%

    No Known Activations