© 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. 18674
    Prev
    Next
    INDEX
    Explanations

    article references within a historical or academic context

    oai_token-act-pair · gpt-3.5-turbo

    brackets or other enclosing symbols

    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
     stalls
    -0.71
    ateurs
    -0.65
     thrott
    -0.65
    nesday
    -0.64
     simulate
    -0.62
     stands
    -0.62
     Opportun
    -0.62
     sinks
    -0.61
     Takes
    -0.60
     proportional
    -0.60
    POSITIVE LOGITS
    note
    1.23
    ...]
    1.21
    Pg
    1.19
    âĢ¦]
    1.05
    Footnote
    0.94
    reviewed
    0.93
    ?]
    0.89
    Note
    0.89
    ].
    0.88
    etc
    0.87
    Activations Density 0.020%

    No Known Activations