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. 8801
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols typically associated with markup or referencing formats in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Increases the logits of tokens that start with the character "g" (case insensitive)

    Explanation Uploaded by User
    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
    •EggList

    No Comments

    Negative Logits
    imen
    -0.75
     undert
    -0.73
     Nightmare
    -0.70
    owski
    -0.67
     upt
    -0.66
    eki
    -0.66
    023
    -0.66
     stri
    -0.65
     Abbey
    -0.65
    ascript
    -0.65
    POSITIVE LOGITS
    Gs
    1.26
    G
    1.24
    g
    1.22
    GY
    1.19
    gm
    1.10
    gs
    1.10
    GH
    1.09
    gian
    1.07
    GS
    1.07
    ge
    1.07
    Activations Density 0.225%

    No Known Activations