© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 1567
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a large quantity or degree

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "much" and its variations to indicate quantity or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    İĭ
    -0.79
    ocamp
    -0.73
    sylv
    -0.73
    ysc
    -0.72
    emy
    -0.70
    etts
    -0.69
    pta
    -0.69
    agate
    -0.69
    opers
    -0.67
    yss
    -0.66
    POSITIVE LOGITS
     ado
    1.07
     simpler
    0.90
     nicer
    0.85
     larger
    0.82
     smaller
    0.80
     cheaper
    0.78
     appreciated
    0.78
     more
    0.77
     stricter
    0.77
     less
    0.75
    Activations Density 0.066%

    No Known Activations