© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 15673
    Prev
    Next
    INDEX
    Explanations

    keywords related to positions in sports

    oai_token-act-pair · gpt-3.5-turbo

    terms related to positional references in sports contexts, specifically "back" and "front"

    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
    cean
    -0.63
     Rev
    -0.63
     Private
    -0.59
    ises
    -0.58
     Lans
    -0.58
     Uruguay
    -0.57
     Crime
    -0.57
     Proud
    -0.56
     mun
    -0.56
     Freedom
    -0.55
    POSITIVE LOGITS
    court
    1.20
    seven
    1.14
    rower
    0.88
    nine
    0.87
    stop
    0.85
    six
    0.84
    ped
    0.83
    cour
    0.82
    door
    0.81
    season
    0.80
    Activations Density 0.067%

    No Known Activations