© 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. 10-RES-JB
    11. 12876
    Prev
    Next
    INDEX
    Explanations

    sports scores in the format of team A's score followed by team B's score

    oai_token-act-pair · gpt-3.5-turbo

    scores or outcomes of sports events

    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
     swearing
    -0.72
    enegger
    -0.69
    igmat
    -0.67
     skelet
    -0.61
     trem
    -0.60
     descriptions
    -0.58
     pict
    -0.58
     tabl
    -0.58
     obe
    -0.57
     sway
    -0.57
    POSITIVE LOGITS
    vs
    1.00
    ND
    0.94
    ½
    0.89
    Aren
    0.88
    GG
    0.85
    LCS
    0.83
    DS
    0.81
    NP
    0.80
    nd
    0.78
    rd
    0.78
    Activations Density 0.063%

    No Known Activations