© 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. 10-RES-JB
    11. 5196
    Prev
    Next
    INDEX
    Explanations

    phrases related to successful completion or achievement

    oai_token-act-pair · gpt-3.5-turbo

    phrases associated with events or occurrences in the past

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    unknown
    -0.76
    only
    -0.75
    ĸļ
    -0.75
    advertising
    -0.74
    sole
    -0.74
    é¾įå¥ij士
    -0.72
    instead
    -0.71
    nor
    -0.70
    Only
    -0.70
    Never
    -0.70
    POSITIVE LOGITS
     occasionally
    0.98
     occasional
    0.96
     exceptions
    0.83
     faults
    0.79
     some
    0.76
     SOME
    0.75
     anecd
    0.75
     exist
    0.74
     technically
    0.74
     theoretically
    0.73
    Activations Density 0.291%

    No Known Activations