© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 33589
    Prev
    Next
    INDEX
    Explanations

    text related to obituaries and tragic events

    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
    430
    +0.07
    0.6%
    121
    +0.06
    0.5%
    458
    +0.06
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    345
    +0.07
    0.08
    464
    +0.06
    0.09
    687
    +0.06
    0.08
    Negative Logits
    imei
    -0.40
    0000000000000000
    -0.39
    tein
    -0.35
    omsky
    -0.35
    \<
    -0.34
    abolic
    -0.34
    Sense
    -0.33
    nai
    -0.33
    ception
    -0.33
     underest
    -0.32
    POSITIVE LOGITS
    allery
    0.46
    LOG
    0.44
    thumbnails
    0.42
    bilt
    0.41
     Seym
    0.40
     FILE
    0.40
     Photos
    0.38
     VIDEOS
    0.38
    sit
    0.37
     Brend
    0.36
    Activations Density 2.550%

    No Known Activations