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. 9-RES-JB
    6. 21784
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    the presence of empty sections or placeholders in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     joke
    -0.69
     Emails
    -0.67
     acron
    -0.67
     LORD
    -0.65
     WATCHED
    -0.64
     Carbuncle
    -0.64
     Remastered
    -0.64
     radios
    -0.64
     beams
    -0.63
     acceler
    -0.63
    POSITIVE LOGITS
    akh
    1.02
    airo
    1.01
    angan
    0.99
    uta
    0.97
    inav
    0.97
    ansk
    0.96
    ascus
    0.96
    isbury
    0.93
    apan
    0.93
    uka
    0.93
    Activations Density 0.152%

    No Known Activations