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. 8-RES-JB
    6. 15663
    Prev
    Next
    INDEX
    Explanations

    programming code syntax and instructions

    oai_token-act-pair · gpt-3.5-turbo

    structured information or data formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ħ¢
    -0.56
    */(
    -0.51
     actionGroup
    -0.50
     Frazier
    -0.50
     ATK
    -0.48
     TW
    -0.47
     Quan
    -0.46
     BART
    -0.46
     aisle
    -0.46
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.45
    POSITIVE LOGITS
    omsky
    0.67
    anwhile
    0.60
    ratulations
    0.56
    aturdays
    0.53
     amuse
    0.50
     Mahm
    0.50
    emetery
    0.49
     Gö
    0.47
    oeuv
    0.47
    escription
    0.47
    Activations Density 1.693%

    No Known Activations