© 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. 4-RES-JB
    11. 10239
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jri
    -0.90
     deferred
    -0.79
    ortium
    -0.76
     cler
    -0.76
     tolerated
    -0.73
    arf
    -0.72
     succumbed
    -0.69
    imar
    -0.67
    rehensive
    -0.66
     reverted
    -0.65
    POSITIVE LOGITS
    ï¸
    0.72
    iov
    0.71
     ANGEL
    0.69
    stories
    0.68
     æľ
    0.65
     img
    0.64
    dimension
    0.64
    Mich
    0.63
    mem
    0.63
     creator
    0.63
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.