© 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. 8-RES-JB
    11. 6407
    Prev
    Next
    INDEX
    Explanations

    applications of examples or visual aids

    oai_token-act-pair · gpt-3.5-turbo

    periods at the end of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     neutrality
    -0.64
    rawdownloadcloneembedreportprint
    -0.56
     preparations
    -0.55
     premature
    -0.53
     fundamentals
    -0.51
     publishers
    -0.51
     Trophy
    -0.51
     sway
    -0.51
     distraction
    -0.51
     momentum
    -0.50
    POSITIVE LOGITS
     coli
    0.84
    g
    0.83
    e
    0.79
    hower
    0.78
    viously
    0.75
    gger
    0.75
    gart
    0.74
    hart
    0.73
    eg
    0.73
    ather
    0.71
    Activations Density 0.032%

    No Known Activations