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

    Neuronpedia

    APICircuit 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. 9-RES-JB
    6. 20997
    Prev
    Next
    INDEX
    Explanations

    character strings involving 'vis-', possibly related to comparing or visualizing situations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to visual representation or visual analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    hyphens and connecting words or characters between words, particularly with "vis-à-vis" or similar hyphenated phrases.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @cedarren
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ufact
    -0.90
    gemony
    -0.73
    enko
    -0.71
    orld
    -0.65
     Chest
    -0.61
    holm
    -0.60
     Bread
    -0.59
     Diplom
    -0.59
    ghai
    -0.58
    atures
    -0.58
    POSITIVE LOGITS
    iard
    0.74
    illes
    0.69
    Downloadha
    0.68
    PsyNetMessage
    0.68
    rentice
    0.68
    ा
    0.67
    Ö¼
    0.67
    anamo
    0.64
    ̶
    0.64
    å¦
    0.62
    Activations Density 0.269%

    No Known Activations