Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 8486
    Prev
    Next
    INDEX
    Explanations

    phrases indicating importance, value, or focus

    oai_token-act-pair · gpt-3.5-turbo

    phrases introducing significant concepts or statements

    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
    robe
    -0.64
    say
    -0.63
    aciously
    -0.63
    order
    -0.62
    ahime
    -0.62
    hip
    -0.62
    mission
    -0.61
    pointer
    -0.61
    erton
    -0.61
    due
    -0.59
    POSITIVE LOGITS
     bothers
    1.32
     distinguishes
    1.23
     happens
    1.23
     separates
    1.20
     happened
    1.16
     mattered
    1.13
     bothered
    1.09
     hurts
    1.00
     pops
    1.00
     sticks
    1.00
    Activations Density 0.137%

    No Known Activations