© 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
    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. 13994
    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
    porting
    -0.88
    porter
    -0.72
    aid
    -0.68
    ported
    -0.66
    onduct
    -0.65
     Kev
    -0.65
    ategory
    -0.63
    aughed
    -0.63
    ports
    -0.63
    uclear
    -0.62
    POSITIVE LOGITS
     quarry
    0.74
    leck
    0.71
     plaque
    0.65
    lik
    0.65
    bucks
    0.61
    azeera
    0.61
    flation
    0.61
     stake
    0.61
     mortar
    0.60
    redients
    0.59
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.