© 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. 22758
    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
    udic
    -0.84
    ota
    -0.71
    apsed
    -0.70
    rower
    -0.69
    lies
    -0.68
    earance
    -0.68
    icular
    -0.67
    apses
    -0.66
    istries
    -0.66
    akeru
    -0.65
    POSITIVE LOGITS
    OPA
    0.61
     Hunts
    0.60
     Harmony
    0.60
     Helm
    0.58
     Maid
    0.56
     Pixie
    0.56
    IJ
    0.56
     Bast
    0.56
     Nobody
    0.55
     Minotaur
    0.54
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.