© 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. 17663
    Prev
    Next
    INDEX
    Explanations

    questions or statements asking for an explanation

    oai_token-act-pair · gpt-3.5-turbo

    questions or phrases that inquire about knowledge or understanding

    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
    Ń·
    -0.68
    ulic
    -0.63
    krit
    -0.63
    ĸļ
    -0.62
    ortality
    -0.62
    æĺ¯
    -0.61
    hig
    -0.61
    uated
    -0.60
    ³
    -0.60
    akening
    -0.57
    POSITIVE LOGITS
     happens
    1.21
     kind
    1.14
     kinds
    1.13
     happened
    1.10
     else
    1.09
     constitutes
    1.00
     type
    0.94
     sort
    0.93
     bothers
    0.90
     happ
    0.86
    Activations Density 0.085%

    No Known Activations