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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 7-RES-JB
    6. 7063
    Prev
    Next
    INDEX
    Explanations

    comparisons between different entities or concepts

    oai_token-act-pair · gpt-3.5-turbo

    comparative statements or discussions about intelligence, morality, and various attributes of subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    links
    -0.61
    audi
    -0.59
    Hung
    -0.59
    flush
    -0.57
    rehens
    -0.55
    Weather
    -0.55
    sych
    -0.53
    Reb
    -0.53
     Winds
    -0.53
    Chance
    -0.53
    POSITIVE LOGITS
     insofar
    0.93
     anyway
    0.80
     irrespective
    0.77
     whereas
    0.77
     because
    0.77
    because
    0.75
     regardless
    0.73
     everywhere
    0.71
     unless
    0.68
     anyways
    0.68
    Activations Density 0.518%

    No Known Activations