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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 504
    Prev
    Next
    INDEX
    Explanations

    terms related to physical injuries like scars

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of scars and the scars' implications, whether physical or emotional

    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
    hower
    -0.79
    £ı
    -0.79
    ĨĴ
    -0.73
    ostics
    -0.73
    gaard
    -0.71
    ablishment
    -0.69
    ictionary
    -0.67
    ullivan
    -0.67
     stale
    -0.65
    eger
    -0.64
    POSITIVE LOGITS
    red
    1.02
    ring
    0.98
    lets
    0.93
    pered
    0.93
    crow
    0.92
    fing
    0.90
    uler
    0.89
    lett
    0.86
    abs
    0.86
    ifiable
    0.85
    Activations Density 0.021%

    No Known Activations