© 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. 4-RES-JB
    11. 14863
    Prev
    Next
    INDEX
    Explanations

    specific actions or processes (e.g., performing, taking, issuing, calculating, detecting, conducting) within a context of data analysis or investigation

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to actions or processes performed in studies or investigations

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

    No Comments

    Negative Logits
    wings
    -0.76
     humble
    -0.70
    dom
    -0.66
     heirs
    -0.62
     stripes
    -0.61
     commanding
    -0.61
     vantage
    -0.61
    mare
    -0.61
    Pr
    -0.61
    abs
    -0.60
    POSITIVE LOGITS
    itored
    0.84
    ioxide
    0.80
     Corker
    0.80
    ãĥ¼ãĥĨ
    0.77
    ĸļ
    0.75
     Parenthood
    0.75
    iasco
    0.73
    ãĤ´
    0.72
     Helpful
    0.69
    chnology
    0.69
    Activations Density 0.308%

    No Known Activations