© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8490
    Prev
    Next
    INDEX
    Explanations

    names of people, locations, and specific numerical information

    oai_token-act-pair · gpt-3.5-turbo

    references to historical or statistical comparisons

    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
    amina
    -0.64
    wrong
    -0.57
     hereby
    -0.57
    gently
    -0.56
     behalf
    -0.55
    istrate
    -0.55
     beh
    -0.53
    Production
    -0.53
     Judicial
    -0.53
    osterone
    -0.52
    POSITIVE LOGITS
     counterparts
    0.84
     predecessors
    0.76
     equivalents
    0.71
     or
    0.71
     circa
    0.67
    ().
    0.65
    eval
    0.62
    ®,
    0.62
     struggles
    0.61
    '.
    0.61
    Activations Density 0.578%

    No Known Activations