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. 23098
    Prev
    Next
    INDEX
    Explanations

    short sentences, headlines, or labels at the beginning or end of text segments

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "This" at the beginning of sentences or clauses

    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
    sic
    -0.79
     srfAttach
    -0.76
     respons
    -0.69
    fully
    -0.69
     actionGroup
    -0.68
     encour
    -0.68
    forth
    -0.66
     versa
    -0.65
     externalToEVAOnly
    -0.64
     remem
    -0.63
    POSITIVE LOGITS
    zbollah
    0.91
     Updated
    0.83
     Vegan
    0.73
    anmar
    0.72
     Transcript
    0.70
     Wrestling
    0.70
    Welcome
    0.69
     Expand
    0.69
    chwitz
    0.69
    Update
    0.68
    Activations Density 0.283%

    No Known Activations