© 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. 23028
    Prev
    Next
    INDEX
    Explanations

    phrases related to action or impact

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to emotional responses and social interactions

    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
     conclud
    -0.67
     exting
    -0.65
    ãĥ¯ãĥ³
    -0.60
    sequently
    -0.55
    ufficient
    -0.53
    vertisement
    -0.52
    alde
    -0.51
    ulations
    -0.51
    livious
    -0.51
    querque
    -0.50
    POSITIVE LOGITS
     me
    1.23
     us
    1.14
     thee
    1.10
     you
    1.09
     ya
    1.02
     YOU
    0.91
    you
    0.90
     him
    0.89
     Him
    0.71
     You
    0.70
    Activations Density 0.584%

    No Known Activations