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. 0-RES-JB
    6. 3152
    Prev
    Next
    INDEX
    Explanations

    verbs related to change or overthrow

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the act of overthrowing or rebellion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     entitled
    -0.69
     availability
    -0.68
     fulfillment
    -0.67
     vi
    -0.65
     Amos
    -0.63
     ATL
    -0.62
     tapes
    -0.61
     lane
    -0.61
     Vor
    -0.60
     Fran
    -0.60
    POSITIVE LOGITS
    rown
    4.54
    rowing
    2.29
    rows
    1.91
    row
    1.53
    rew
    1.43
    rower
    1.40
    rowd
    1.30
    rafted
    1.22
     Crown
    1.14
    rowth
    1.09
    Activations Density 0.008%

    No Known Activations