© 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. 2-RES-JB
    11. 23191
    Prev
    Next
    INDEX
    Explanations

    abbreviations or codes related to specific organizations or programs

    oai_token-act-pair · gpt-3.5-turbo

    references to the "MT" designation, likely indicating a specific entity or classification related to it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hold
    -0.88
    pta
    -0.63
     Horowitz
    -0.62
     Dunham
    -0.61
    flies
    -0.61
     Fulton
    -0.59
     Pog
    -0.59
     Hurricanes
    -0.58
     Comet
    -0.58
     cider
    -0.58
    POSITIVE LOGITS
    MT
    1.13
    ypes
    0.87
    TL
    0.83
    ullah
    0.82
    ertodd
    0.80
    ument
    0.75
    ORPG
    0.73
    ength
    0.73
    TP
    0.73
    TE
    0.72
    Activations Density 0.007%

    No Known Activations