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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 7-RES-JB
    6. 17428
    Prev
    Next
    INDEX
    Explanations

    proper nouns such as names of locations, organizations, and individuals

    oai_token-act-pair · gpt-3.5-turbo

    parentheses and their related context in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oooooooooooooooo
    -0.72
    zos
    -0.65
     blo
    -0.64
    (*
    -0.63
    arton
    -0.62
    choes
    -0.61
    blers
    -0.60
    yip
    -0.60
    hang
    -0.59
    cdn
    -0.59
    POSITIVE LOGITS
     constitu
    0.80
     ILCS
    0.71
     Frames
    0.69
     Committees
    0.67
     COUNTY
    0.67
     Tonight
    0.66
     âĵĺ
    0.62
     Latest
    0.62
     Polk
    0.62
     MEN
    0.61
    Activations Density 0.055%

    No Known Activations