© 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. 4-RES-JB
    11. 3732
    Prev
    Next
    INDEX
    Explanations

    words or phrases associated with things that are well-known or remarkable

    oai_token-act-pair · gpt-3.5-turbo

    references to significant or noteworthy elements in a text

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

    No Comments

    Negative Logits
    ©¶æ
    -0.96
    claimer
    -0.89
    nery
    -0.77
    nan
    -0.75
    prep
    -0.74
    vacc
    -0.72
    uddled
    -0.72
    ceans
    -0.69
    imeter
    -0.69
    anguage
    -0.69
    POSITIVE LOGITS
     landmarks
    0.96
     exceptions
    0.94
     accomplishments
    0.91
     milestones
    0.91
    Notable
    0.90
     exception
    0.89
    NESS
    0.84
     notable
    0.82
     achievements
    0.79
     accomplishment
    0.78
    Activations Density 0.020%

    No Known Activations