© 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. 8-RES-JB
    11. 15201
    Prev
    Next
    INDEX
    Explanations

    sporting event scores and statistics

    oai_token-act-pair · gpt-3.5-turbo

    references to scores or statistical data related to sports games

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     puberty
    -0.71
     solicitation
    -0.70
     SX
    -0.70
     Loll
    -0.69
     literature
    -0.67
     lecture
    -0.64
     BDS
    -0.63
     Chop
    -0.61
     appraisal
    -0.61
     AMC
    -0.61
    POSITIVE LOGITS
    straight
    1.16
    iron
    1.10
    win
    1.03
    percent
    1.02
    point
    1.01
    game
    0.98
    year
    0.98
    inch
    0.98
    sided
    0.96
    pointer
    0.96
    Activations Density 0.077%

    No Known Activations