© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 23820
    Prev
    Next
    INDEX
    Explanations

    terms related to scoring in sports

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "scored" along with the corresponding numbers related to points or goals in sports contexts

    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
    agan
    -0.86
    lly
    -0.76
    pora
    -0.69
    esan
    -0.68
    tan
    -0.68
    fer
    -0.68
    ned
    -0.67
    alg
    -0.66
    ships
    -0.65
    conn
    -0.63
    POSITIVE LOGITS
     scored
    0.95
     scoring
    0.87
     scores
    0.82
     score
    0.81
    ificant
    0.81
    card
    0.77
    ific
    0.75
     scorer
    0.74
    otle
    0.73
    umbles
    0.73
    Activations Density 0.013%

    No Known Activations