© 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. 2-RES-JB
    11. 9315
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cial
    -0.92
    merce
    -0.78
    Interstitial
    -0.75
    interstitial
    -0.73
    swick
    -0.73
    cially
    -0.72
    nw
    -0.72
    LV
    -0.70
    nell
    -0.69
     Genius
    -0.67
    POSITIVE LOGITS
     cutoff
    0.72
     veto
    0.72
     coerc
    0.72
     stakes
    0.70
     membership
    0.69
     prosec
    0.68
     rul
    0.68
    anamo
    0.65
     backing
    0.65
     steering
    0.64
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.