© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 41
    Prev
    Next
    INDEX
    Explanations

    It appears that neuron 4 does not activate for any of the provided tokens, which suggests it might be looking for something not present in the provided text excerpts or that it might be malfunctioning or inactive

    oai_token-act-pair · gpt-4-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    latest
    -0.72
    ache
    -0.72
     awa
    -0.68
    dylib
    -0.67
    notations
    -0.67
    ++)
    -0.66
     residues
    -0.64
    google
    -0.64
    soever
    -0.63
    Ĥİ
    -0.63
    POSITIVE LOGITS
     Watt
    0.73
    rouse
    0.71
    nect
    0.68
    uras
    0.68
    ner
    0.67
     Buk
    0.62
    aan
    0.62
    ners
    0.62
    slave
    0.60
    rament
    0.59
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.