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. 16506
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "illy" in text

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of the term "illy" 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
    rity
    -0.77
    ually
    -0.77
    sworth
    -0.75
    VERTISEMENT
    -0.75
    estation
    -0.74
    obal
    -0.74
    amara
    -0.73
    orers
    -0.73
    ial
    -0.71
    lain
    -0.70
    POSITIVE LOGITS
    ield
    0.77
     Circus
    0.76
    yy
    0.70
    mph
    0.69
     Xie
    0.67
    gm
    0.67
     Pry
    0.64
    puff
    0.64
    illy
    0.64
     stroll
    0.64
    Activations Density 0.037%

    No Known Activations