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. 4495
    Prev
    Next
    INDEX
    Explanations

    names, especially those with 'z' sounds

    oai_token-act-pair · gpt-3.5-turbo

    names and titles related to notable figures and their affiliations

    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
     Allaah
    -0.77
     Coral
    -0.64
    romeda
    -0.64
     Vietnamese
    -0.63
     Concord
    -0.63
     Luther
    -0.61
     GOODMAN
    -0.60
     Catalyst
    -0.60
    HAM
    -0.59
    clusive
    -0.58
    POSITIVE LOGITS
    ÅĤ
    1.45
    kowski
    1.27
    cz
    1.26
    zyk
    1.19
    owski
    1.16
    zynski
    1.13
    ewski
    1.13
    Ä
    1.12
    iewicz
    1.09
    iak
    1.09
    Activations Density 0.158%

    No Known Activations