© 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. 2-RES-JB
    11. 9355
    Prev
    Next
    INDEX
    Explanations

    references to sports teams in a competitive context

    oai_token-act-pair · gpt-3.5-turbo

    references to a sports team

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tml
    -0.76
    ranging
    -0.75
    fect
    -0.75
     Maw
    -0.74
    pire
    -0.72
    skinned
    -0.71
    lear
    -0.71
    tain
    -0.71
    CV
    -0.68
    forward
    -0.67
    POSITIVE LOGITS
     mates
    1.18
    mates
    1.01
     mate
    0.88
     scrimmage
    0.86
     manager
    0.82
     rosters
    0.81
     coached
    0.76
     teams
    0.76
     captains
    0.76
    members
    0.75
    Activations Density 0.059%

    No Known Activations