© 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. 36890
    Prev
    Next
    INDEX
    Explanations

    instances where the word "over" is used emphatically or within contexts related to excessive or heightened states

    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
    +0.20
    0.8%
    526
    +0.14
    0.6%
    260
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    260
    +0.20
    0.10
    269
    +0.14
    0.05
    684
    +0.14
    0.05
    Negative Logits
    arium
    -0.86
     Lauder
    -0.84
    illary
    -0.78
    ":[
    -0.78
    uary
    -0.74
    UES
    -0.74
     partName
    -0.71
    UE
    -0.71
    ittal
    -0.70
    ORY
    -0.69
    POSITIVE LOGITS
    drive
    1.35
    hang
    1.31
    priced
    1.25
    loading
    1.18
    haul
    1.18
    tones
    1.16
    kill
    1.14
    whelming
    1.14
    grown
    1.13
    valued
    1.12
    Activations Density 7.195%

    No Known Activations