© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 21157
    Prev
    Next
    INDEX
    Explanations

    proper names or locations

    oai_token-act-pair · gpt-3.5-turbo

    specific news station identifiers or code names associated with news reports

    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
    pora
    -0.77
    acca
    -0.74
     disinfect
    -0.67
     burner
    -0.65
     pointers
    -0.63
     hiber
    -0.63
    anmar
    -0.62
    footed
    -0.62
    aceae
    -0.61
     sep
    -0.61
    POSITIVE LOGITS
    TV
    1.05
    GBT
    0.98
    CTV
    0.87
    NBC
    0.86
    IX
    0.86
    ABC
    0.85
    Alert
    0.83
    JR
    0.83
    FOX
    0.82
    VT
    0.82
    Activations Density 0.072%

    No Known Activations