© 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. 24402
    Prev
    Next
    INDEX
    Explanations

    mentions of American football positions and roles, specifically "wide receiver" and "tight end."

    oai_token-act-pair · gpt-3.5-turbo

    references to wide receivers and tight ends in football contexts

    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
     UNESCO
    -0.79
    heit
    -0.75
    xit
    -0.74
    INESS
    -0.72
    ĸļ
    -0.70
     Nicotine
    -0.68
     Editorial
    -0.67
    zzle
    -0.67
     Catalyst
    -0.67
    ZZ
    -0.67
    POSITIVE LOGITS
    team
    0.99
     winger
    0.93
     linebackers
    0.93
     fullback
    0.89
     leagues
    0.88
     coach
    0.87
     linebacker
    0.87
     league
    0.81
     scorer
    0.81
     infield
    0.80
    Activations Density 0.131%

    No Known Activations