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. 10477
    Prev
    Next
    INDEX
    Explanations

    hyperlinks or directions indicated in a text

    oai_token-act-pair · gpt-3.5-turbo

    references to content or information located beneath other elements in the document

    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
    æ©
    -0.63
    BuyableInstoreAndOnline
    -0.62
    vere
    -0.61
    iet
    -0.60
    ãĥı
    -0.60
     plurality
    -0.58
    mt
    -0.58
    ãĥ³ãĤ¸
    -0.58
    onte
    -0.55
    vati
    -0.54
    POSITIVE LOGITS
    .):
    0.84
    ground
    0.82
    !:
    0.79
    :-
    0.75
    :
    0.74
     illustrating
    0.73
    !
    0.73
    .
    0.73
     âĨ
    0.72
    ebin
    0.72
    Activations Density 0.048%

    No Known Activations