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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 5-RES-JB
    6. 1757
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names such as "Owens" and terms related to user experience design (UX)

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals named Owens and aspects related to user experience (UX) design

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anche
    -0.80
     Paramount
    -0.69
    aghd
    -0.66
     anat
    -0.63
    zman
    -0.62
     caric
    -0.61
    money
    -0.61
     reprim
    -0.60
    mand
    -0.60
    bath
    -0.59
    POSITIVE LOGITS
    alez
    0.86
    baum
    0.80
    ufact
    0.73
    velength
    0.70
    ener
    0.70
    CRIP
    0.69
    chwitz
    0.68
    adow
    0.67
    ield
    0.67
    ibling
    0.66
    Activations Density 0.062%

    No Known Activations