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. 24215
    Prev
    Next
    INDEX
    Explanations

    adjectives describing the quality or strength of something

    oai_token-act-pair · gpt-3.5-turbo

    adjectives that describe qualities or characteristics

    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
    psc
    -0.62
    ango
    -0.55
    Bed
    -0.55
    cknow
    -0.55
    rahim
    -0.50
     Proc
    -0.49
     dstg
    -0.48
    SON
    -0.47
    ç«
    -0.47
     Warehouse
    -0.46
    POSITIVE LOGITS
     as
    1.29
    as
    0.94
     AS
    0.80
    idious
    0.70
     As
    0.68
    asin
    0.66
     anymore
    0.65
    As
    0.64
    istani
    0.64
     a
    0.62
    Activations Density 0.114%

    No Known Activations