© 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. 7023
    Prev
    Next
    INDEX
    Explanations

    words related to sports events or possibly names of players and teams

    oai_token-act-pair · gpt-3.5-turbo

    specific names and identifiers related to games or sports events

    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
    .).
    -0.88
    .),
    -0.81
    )."
    -0.79
    âĢ¦)
    -0.76
    .)
    -0.73
    cause
    -0.73
    staking
    -0.71
    .")
    -0.69
    depending
    -0.69
    !),
    -0.68
    POSITIVE LOGITS
     Jr
    0.79
     feat
    0.76
    IRO
    0.71
     Pt
    0.70
     pt
    0.70
     vs
    0.69
     Presents
    0.68
     ft
    0.64
     LV
    0.64
    Jr
    0.64
    Activations Density 0.174%

    No Known Activations