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. 18168
    Prev
    Next
    INDEX
    Explanations

    phrases related to programming and technology, specifically focused on coding languages and resources

    oai_token-act-pair · gpt-3.5-turbo

    references to various forms of media, particularly books and songs

    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
    utterstock
    -0.64
    âĢij
    -0.61
    repre
    -0.59
     «
    -0.58
    ĪĴ
    -0.57
    surprisingly
    -0.55
     appropri
    -0.55
    ivably
    -0.54
    etheless
    -0.53
    bably
    -0.53
    POSITIVE LOGITS
    ")
    2.24
    ").
    2.22
    !".
    2.20
    "!
    2.19
    %"
    2.18
    ",
    2.17
    ".
    2.16
    "?
    2.14
    ";
    2.11
    !",
    2.11
    Activations Density 0.638%

    No Known Activations