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. 4260
    Prev
    Next
    INDEX
    Explanations

    keywords related to reading and writing data in a technical context

    oai_token-act-pair · gpt-3.5-turbo

    instances of reading and writing actions or functions in a technical context

    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
    xon
    -0.71
    opard
    -0.63
     Gamble
    -0.59
    ño
    -0.58
    Las
    -0.58
     halftime
    -0.58
    اÙĦ
    -0.57
     Zur
    -0.57
     rolling
    -0.56
    ality
    -0.55
    POSITIVE LOGITS
     aloud
    1.40
    just
    1.28
     comprehension
    1.13
    ying
    1.11
    write
    1.08
    dress
    1.06
    mission
    1.04
    ahead
    1.03
    mitted
    1.01
    ied
    1.00
    Activations Density 0.053%

    No Known Activations