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. 11-RES-JB
    6. 8737
    Prev
    Next
    INDEX
    Explanations

    long multisyllabic foreign words with special characters

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and symbols associated with structuring information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    htaking
    -0.77
    urances
    -0.76
    ubes
    -0.71
    hesda
    -0.71
    istries
    -0.69
    ocent
    -0.68
    athing
    -0.68
    uties
    -0.68
    epad
    -0.67
    eches
    -0.66
    POSITIVE LOGITS
    pron
    1.30
     abbre
    1.24
     abbrevi
    1.22
     pronounced
    1.20
     acronym
    1.11
     shorthand
    1.10
     Literally
    1.09
     slang
    1.04
     literally
    1.04
     hereafter
    1.03
    Activations Density 0.185%

    No Known Activations