© 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. 15272
    Prev
    Next
    INDEX
    Explanations

    HTML and coding elements related to formatting and styling

    oai_token-act-pair · gpt-3.5-turbo

    HTML or XML-like tags and syntax structures

    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
     Hastings
    -0.83
    ingham
    -0.73
    eed
    -0.70
     Whedon
    -0.63
     Winc
    -0.63
    hyde
    -0.62
     Templ
    -0.62
    ately
    -0.61
     Bleach
    -0.59
     Dalton
    -0.58
    POSITIVE LOGITS
    wcsstore
    1.02
    rade
    0.76
    rag
    0.76
    netic
    0.73
    unknown
    0.69
    helle
    0.66
     Skydragon
    0.66
     minded
    0.66
    picture
    0.65
    strip
    0.65
    Activations Density 0.024%

    No Known Activations