Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 23479
    Prev
    Next
    INDEX
    Explanations

    verbs and nouns related to physical sports maneuvers and impressive feats

    oai_token-act-pair · gpt-3.5-turbo

    terms related to knockout or stoppage in combat sports

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

    No Comments

    Negative Logits
    ris
    -0.75
    rir
    -0.74
    yll
    -0.73
    anson
    -0.71
    reads
    -0.71
     Aerospace
    -0.70
    anamo
    -0.70
    ria
    -0.70
     NRS
    -0.69
    mberg
    -0.69
    POSITIVE LOGITS
     knockout
    1.32
     punch
    0.91
    bowl
    0.85
     blow
    0.83
     showdown
    0.82
     trophies
    0.80
     elimination
    0.77
     victories
    0.75
     defeat
    0.75
     Showdown
    0.74
    Activations Density 0.008%

    No Known Activations