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. 23051
    Prev
    Next
    INDEX
    Explanations

    exceptions or conditions that invalidate a general statement

    oai_token-act-pair · gpt-3.5-turbo

    the word "except" and its variations used in context

    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
    ushed
    -0.63
    mob
    -0.63
    gged
    -0.63
    ossom
    -0.62
    acia
    -0.62
    ushing
    -0.62
    Äĩ
    -0.61
    uld
    -0.60
    avan
    -0.60
    yrs
    -0.59
    POSITIVE LOGITS
    ional
    1.06
     insofar
    0.82
    heses
    0.75
    livious
    0.67
    inarily
    0.64
    arus
    0.63
     except
    0.62
    ¯
    0.61
    icularly
    0.61
    withstanding
    0.61
    Activations Density 0.023%

    No Known Activations