© 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. 7714
    Prev
    Next
    INDEX
    Explanations

    phrases related to capturing attention or interest

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to capture or 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
    anasia
    -0.67
    mere
    -0.64
    ignty
    -0.63
    :,
    -0.62
    partial
    -0.62
    ————
    -0.61
     autonomy
    -0.59
    abama
    -0.59
     Secondly
    -0.59
     latitude
    -0.58
    POSITIVE LOGITS
     hearts
    1.12
     viewers
    1.06
     minds
    1.05
     audiences
    1.02
     listeners
    1.00
     readers
    1.00
     peoples
    0.96
     jaws
    0.96
     onlook
    0.92
     everyone
    0.91
    Activations Density 0.238%

    No Known Activations