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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 723
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anooga
    -0.82
    cks
    -0.79
    ija
    -0.75
    mingham
    -0.75
    azine
    -0.69
    nex
    -0.69
    elia
    -0.68
    ioned
    -0.68
    iots
    -0.67
    icrobial
    -0.67
    POSITIVE LOGITS
     prosecut
    0.76
    Topic
    0.68
    Developer
    0.67
    Prosecut
    0.65
    Member
    0.62
     concession
    0.62
    Veter
    0.62
    OIL
    0.61
    ROR
    0.60
     Methodist
    0.59
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.