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. 1-RES-JB
    6. 8343
    Prev
    Next
    INDEX
    Explanations

    URLs in the text

    oai_token-act-pair · gpt-3.5-turbo

    URLs and web links

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     abst
    -0.77
     Palest
    -0.71
     ter
    -0.68
     estranged
    -0.66
     Gram
    -0.65
     Tart
    -0.65
     unfinished
    -0.64
    cffff
    -0.64
     unsus
    -0.64
     Dele
    -0.63
    POSITIVE LOGITS
    ://
    1.65
    www
    1.31
    doi
    1.21
    http
    1.10
    :/
    0.96
    https
    0.92
    natureconservancy
    0.91
     www
    0.91
    sites
    0.90
    link
    0.88
    Activations Density 0.007%

    No Known Activations