© 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. 7-RES-JB
    11. 3613
    Prev
    Next
    INDEX
    Explanations

    terms related to governmental bodies or organizations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of a specific word pattern related to "council."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FORE
    -0.81
    HAEL
    -0.70
    urga
    -0.70
     TAM
    -0.66
    ANC
    -0.66
    RGB
    -0.65
    ################
    -0.63
    ASED
    -0.62
    ACTION
    -0.61
    IFT
    -0.60
    POSITIVE LOGITS
    ciation
    1.04
    cers
    1.02
    cil
    1.01
    spe
    1.00
    nen
    0.98
    oun
    0.96
    mers
    0.95
    stant
    0.94
    cer
    0.93
    emouth
    0.90
    Activations Density 0.025%

    No Known Activations