© 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. 9502
    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
     choked
    -0.70
    seless
    -0.69
    dyl
    -0.69
    Haunted
    -0.69
    gotten
    -0.67
    ieties
    -0.66
    iances
    -0.63
    bus
    -0.63
    blems
    -0.62
    ¶
    -0.62
    POSITIVE LOGITS
     precursor
    0.73
     NF
    0.72
     FP
    0.69
    ETF
    0.69
     NL
    0.68
     [*
    0.65
    opa
    0.64
     breadth
    0.63
     NP
    0.63
     gol
    0.62
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.