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. 2-RES-JB
    6. 13284
    Prev
    Next
    INDEX
    Explanations

    instances where the word "Both" is followed by a comparison or list of related elements

    oai_token-act-pair · gpt-3.5-turbo

    references to collective actions or agreements involving two or more parties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ugu
    -0.74
    lé
    -0.68
    atur
    -0.67
    cycl
    -0.67
    itated
    -0.66
    luence
    -0.65
    krit
    -0.65
    lie
    -0.64
    rir
    -0.63
     upgr
    -0.62
    POSITIVE LOGITS
     sexes
    1.09
     sides
    1.06
     genders
    0.94
     halves
    0.94
     sets
    0.84
     Sets
    0.74
     Ends
    0.72
     parties
    0.71
     formats
    0.71
     thirds
    0.71
    Activations Density 0.017%

    No Known Activations