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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6-RES-JB
    11. 4139
    Prev
    Next
    INDEX
    Explanations

    terms related to national entities or concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to national identity and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    herty
    -0.87
    xual
    -0.87
    ullivan
    -0.77
     Coffin
    -0.72
    YE
    -0.68
    ttes
    -0.67
    essen
    -0.67
    omething
    -0.66
    OHN
    -0.65
    enhagen
    -0.65
    POSITIVE LOGITS
    ised
    1.09
    istic
    1.06
    ities
    1.03
     Geographic
    1.01
    isms
    0.96
    ized
    0.95
    isations
    0.94
     anthem
    0.93
    istically
    0.90
    isation
    0.89
    Activations Density 0.038%

    No Known Activations