© 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. 10223
    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
    hement
    -0.71
    ÏĤ
    -0.65
    iles
    -0.63
     Recovery
    -0.62
    los
    -0.61
     Shepherd
    -0.61
    imus
    -0.60
    Í
    -0.60
     Santos
    -0.60
     scanner
    -0.60
    POSITIVE LOGITS
    NetMessage
    0.83
    wcs
    0.76
    dash
    0.70
     srf
    0.67
     precedent
    0.66
    vp
    0.66
    ¥ŀ
    0.66
    userc
    0.65
    ĸļ
    0.64
     (#
    0.63
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.