© 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. 8-RES-JB
    11. 18573
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Carney
    -0.70
     Claus
    -0.56
     Operator
    -0.56
     Quinn
    -0.55
     Ahmed
    -0.55
    mouth
    -0.54
    é¾į
    -0.54
     Ms
    -0.53
     Ahmad
    -0.53
    LINE
    -0.53
    POSITIVE LOGITS
    rum
    0.72
    ork
    0.69
    awei
    0.67
    hedon
    0.67
     Sorce
    0.66
    zsche
    0.64
    izoph
    0.64
    abwe
    0.63
    assic
    0.62
    lux
    0.61
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.