© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 6934
    Prev
    Next
    INDEX
    Explanations

    information related to software exceptions and technical error messages

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly commas, indicating their frequency in various contexts

    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
    ,
    -0.63
    jured
    -0.59
    ulent
    -0.58
     and
    -0.58
    miah
    -0.58
    itol
    -0.57
     &
    -0.57
    ance
    -0.55
    zbek
    -0.54
    ivity
    -0.53
    POSITIVE LOGITS
     respectively
    1.11
     thereby
    0.99
     thus
    0.90
     albeit
    0.88
     accordingly
    0.81
     whichever
    0.80
     hence
    0.80
     consequently
    0.80
     depending
    0.79
    depending
    0.78
    Activations Density 0.309%

    No Known Activations