© 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. 11-RES-JB
    11. 9218
    Prev
    Next
    INDEX
    Explanations

    ranking or comparison of individuals or entities within a specific category or group

    oai_token-act-pair · gpt-3.5-turbo

    references to player 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 @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agate
    -0.89
    obia
    -0.87
    externalActionCode
    -0.86
    atra
    -0.77
    Flickr
    -0.76
    insula
    -0.75
    utan
    -0.75
    arta
    -0.73
    trip
    -0.72
    chapter
    -0.72
    POSITIVE LOGITS
     players
    1.71
     rookies
    1.67
     starters
    1.57
     quarterbacks
    1.52
     prospects
    1.45
     athletes
    1.42
     candidates
    1.41
     linemen
    1.40
     performers
    1.38
     pitchers
    1.38
    Activations Density 0.259%

    No Known Activations