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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 18499
    Prev
    Next
    INDEX
    Explanations

    unrelated characters or artifacts in the text

    oai_token-act-pair · gpt-3.5-turbo

    sections of text with a high level of numerical or financial significance

    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
     occas
    -0.82
     framing
    -0.81
     eleph
    -0.81
     undermin
    -0.79
     favoring
    -0.76
    aditional
    -0.73
     aging
    -0.73
     favorably
    -0.73
     inactive
    -0.71
     favors
    -0.71
    POSITIVE LOGITS
    Scroll
    1.00
    Liverpool
    0.96
    BBC
    0.95
    Labour
    0.90
    Royal
    0.83
    Els
    0.82
    ³³³³³³³³³³³³³³³³
    0.81
    iona
    0.81
    Manchester
    0.79
    DragonMagazine
    0.79
    Activations Density 0.346%

    No Known Activations