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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 1169
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     flats
    -0.78
    GBT
    -0.72
    ammy
    -0.67
    astern
    -0.66
    aults
    -0.65
     Canyon
    -0.64
    estation
    -0.64
     redes
    -0.64
    mson
    -0.64
    facing
    -0.62
    POSITIVE LOGITS
    ocent
    0.73
    resso
    0.73
    uman
    0.72
    GES
    0.72
    =-=-=-=-=-=-=-=-
    0.66
    aughs
    0.65
    reprene
    0.65
    ĸļ
    0.65
    stasy
    0.60
    GE
    0.60
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.