© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 11796
    Prev
    Next
    INDEX
    Explanations

    phrases related to terms like 'name,' 'deal,' 'number,' 'expectation,' 'price,' 'subject,' 'symbol,' 'product,' 'path,' 'test bed,' 'burden,' 'prey,' 'cure,' 'service,' and 'symbol'

    oai_token-act-pair · gpt-3.5-turbo

    significant nouns that denote key concepts or themes

    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
    tnc
    -0.80
    CRIP
    -0.71
    ãĥīãĥ©
    -0.69
    respect
    -0.69
    é»Ĵ
    -0.66
    Such
    -0.64
    hemy
    -0.61
    such
    -0.60
    axter
    -0.59
    adoes
    -0.59
    POSITIVE LOGITS
    liest
    1.47
    iest
    1.42
    hest
    0.98
    ultimate
    0.93
     equivalent
    0.91
     centerpiece
    0.90
     pinnacle
    0.83
     closest
    0.83
    est
    0.81
    erest
    0.79
    Activations Density 0.304%

    No Known Activations