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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 10752
    Prev
    Next
    INDEX
    Explanations

    numbers related to player statistics in sports

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "on" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ikan
    -0.71
    INESS
    -0.68
    ily
    -0.66
    SourceFile
    -0.63
    waters
    -0.62
    WER
    -0.62
    ptin
    -0.61
    oler
    -0.61
     liter
    -0.60
    reet
    -0.60
    POSITIVE LOGITS
    etime
    1.11
     behalf
    1.09
    erous
    0.97
     occasion
    0.95
    slaught
    0.91
    coming
    0.90
     Mondays
    0.90
    ibaba
    0.89
     steroids
    0.85
    sets
    0.79
    Activations Density 0.190%

    No Known Activations