© 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. 9-RES-JB
    11. 13423
    Prev
    Next
    INDEX
    Explanations

    instances where a source is providing evidence or support for a claim or argument

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "cited" and its variations, indicating references or quotations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quer
    -0.82
    spawn
    -0.77
    jah
    -0.75
    te
    -0.74
    ¯¯¯¯¯¯¯¯
    -0.74
    ire
    -0.72
    Ñı
    -0.71
    mys
    -0.71
    kie
    -0.70
    tes
    -0.70
    POSITIVE LOGITS
     examples
    0.95
     inconsistencies
    0.88
     similarities
    0.85
     unnamed
    0.84
     sources
    0.82
     anecdotes
    0.81
     reasons
    0.79
     statistics
    0.76
     preced
    0.75
     warnings
    0.74
    Activations Density 0.078%

    No Known Activations