© 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. 6-RES-JB
    11. 14890
    Prev
    Next
    INDEX
    Explanations

    numerical rankings related to different statistical categories in sports

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to rankings and statistics in sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rod
    -0.68
    Mask
    -0.63
     interns
    -0.62
    ream
    -0.61
    emb
    -0.60
    Tokens
    -0.59
     maj
    -0.58
     collabor
    -0.58
     differently
    -0.57
     cater
    -0.57
    POSITIVE LOGITS
     overall
    0.77
     Forbes
    0.71
     Alexa
    0.70
    ibaba
    0.69
    anguage
    0.69
     Overall
    0.68
    elsius
    0.68
     Compass
    0.68
     compass
    0.67
    cko
    0.65
    Activations Density 0.087%

    No Known Activations