© 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. 3-RES-JB
    11. 11377
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     shelling
    -0.70
     exhaustion
    -0.63
     Mississippi
    -0.63
     weap
    -0.62
     Verd
    -0.62
     breadth
    -0.58
     Duel
    -0.57
     costing
    -0.56
     gunfire
    -0.56
    roit
    -0.55
    POSITIVE LOGITS
    eln
    0.95
    gins
    0.84
    erial
    0.83
    aunders
    0.82
    aux
    0.76
    veland
    0.75
    iband
    0.75
    ilib
    0.73
    isite
    0.71
    oldown
    0.70
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.