© 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. 10-RES-JB
    11. 5327
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific names and locations

    oai_token-act-pair · gpt-3.5-turbo

    token-like structures, possibly related to identifiers or hashtags

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Zap
    -0.89
     Macro
    -0.82
     Za
    -0.82
     Gateway
    -0.82
     Mog
    -0.82
    674
    -0.79
    660
    -0.79
     Haku
    -0.78
    680
    -0.78
     Gan
    -0.77
    POSITIVE LOGITS
    id
    1.26
    itt
    1.09
    ID
    1.09
    idd
    1.08
    atti
    1.03
    atto
    0.98
    idy
    0.98
    ids
    0.97
    atha
    0.97
    rette
    0.94
    Activations Density 0.193%

    No Known Activations