© 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. 10540
    Prev
    Next
    INDEX
    Explanations

    mentions of specific places and people

    oai_token-act-pair · gpt-3.5-turbo

    instances of the suffix "ach" or its variations and other similar phonetic patterns

    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
     clock
    -0.65
     TODAY
    -0.63
     unanswered
    -0.63
     legacy
    -0.62
     unheard
    -0.61
     unexplained
    -0.60
     pim
    -0.60
     vacant
    -0.59
    =]
    -0.58
     dedicated
    -0.58
    POSITIVE LOGITS
    wana
    0.92
    ani
    0.91
    aji
    0.91
    oti
    0.89
    ako
    0.88
    oud
    0.87
    aj
    0.87
    ala
    0.87
    uz
    0.87
    uko
    0.86
    Activations Density 0.101%

    No Known Activations