© 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. 10-RES-JB
    11. 20295
    Prev
    Next
    INDEX
    Explanations

    instances where the phrase "As you can see" or similar expressions are used

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate observation or perception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    prus
    -0.70
    kefeller
    -0.69
    idity
    -0.67
    enders
    -0.62
    idal
    -0.62
    lling
    -0.61
    lled
    -0.61
    mens
    -0.61
    inki
    -0.60
    rang
    -0.59
    POSITIVE LOGITS
    ,
    0.88
     (),
    0.82
    .,
    0.74
    ,.
    0.73
    ,,
    0.73
    ,-
    0.71
     by
    0.70
    ,,,,
    0.65
    é¾įåĸļ士
    0.65
    (),
    0.65
    Activations Density 0.056%

    No Known Activations