© 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. 6743
    Prev
    Next
    INDEX
    Explanations

    articles that have been published for a specific number of years

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases that indicate the existence of articles or content summaries

    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
    gov
    -0.74
    Bir
    -0.71
    Shape
    -0.71
     looms
    -0.64
    unts
    -0.63
    dds
    -0.61
    sil
    -0.60
    mart
    -0.60
    demand
    -0.59
    ibles
    -0.59
    POSITIVE LOGITS
     conject
    0.96
     sponsored
    0.95
     excerpt
    0.91
     reprinted
    0.91
     outdated
    0.86
     incomplete
    0.84
     deprecated
    0.83
     part
    0.83
     copyrighted
    0.82
     about
    0.82
    Activations Density 0.046%

    No Known Activations