© 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
    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. 16675
    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
     autobi
    -0.64
    amaz
    -0.63
     Athens
    -0.61
     memoir
    -0.60
     Plymouth
    -0.59
    GGGGGGGG
    -0.58
    gger
    -0.57
     verb
    -0.57
    REC
    -0.56
     nowadays
    -0.55
    POSITIVE LOGITS
    fell
    0.74
    ighth
    0.73
    ival
    0.72
    iban
    0.72
    ector
    0.71
    ¬¼
    0.69
    uble
    0.68
    ihad
    0.66
    fixes
    0.66
    DATA
    0.65
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.