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

    Neuronpedia

    APICircuit 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. 4-RES-JB
    6. 21572
    Prev
    Next
    INDEX
    Explanations

    interjections expressing surprise or exclamation

    oai_token-act-pair · gpt-3.5-turbo

    expressions of surprise or realization

    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
    IUM
    -0.83
     Construct
    -0.73
    */(
    -0.73
    eers
    -0.73
    -+-+
    -0.70
     awoken
    -0.69
     Fired
    -0.68
    Introduced
    -0.68
    Registered
    -0.67
    flies
    -0.65
    POSITIVE LOGITS
    umph
    0.97
    hhhh
    0.95
    oho
    0.94
    oh
    0.91
    hh
    0.89
    anian
    0.85
    hhh
    0.82
    warts
    0.82
    Oh
    0.80
    ohan
    0.79
    Activations Density 0.008%

    No Known Activations