© 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. 4751
    Prev
    Next
    INDEX
    Explanations

    phrases relating to comparison or attention

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to media coverage and attention

    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
    eeds
    -0.82
    artifacts
    -0.77
    kinson
    -0.67
    alsa
    -0.66
    nown
    -0.66
    andum
    -0.66
    chini
    -0.64
     VIDEOS
    -0.64
    basketball
    -0.63
    ullivan
    -0.62
    POSITIVE LOGITS
     scrutiny
    1.07
     attention
    1.04
     mention
    1.04
     spotlight
    1.03
     airing
    1.00
     thumbs
    0.95
     boost
    0.90
     moniker
    0.90
     treatment
    0.90
     designation
    0.88
    Activations Density 0.183%

    No Known Activations