© 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. 9-RES-JB
    11. 15714
    Prev
    Next
    INDEX
    Explanations

    adjectives related to nationality or cultural identity

    oai_token-act-pair · gpt-3.5-turbo

    references to the human condition and American identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iHUD
    -0.73
    aryl
    -0.69
    PsyNetMessage
    -0.68
    hots
    -0.68
    theless
    -0.68
    placed
    -0.67
    recent
    -0.67
    ummies
    -0.67
     Rica
    -0.67
    arella
    -0.67
    POSITIVE LOGITS
     psyche
    1.45
     economy
    1.41
     populace
    1.33
     landscape
    1.26
     electorate
    1.24
     universe
    1.22
     imagination
    1.15
     marketplace
    1.13
     workforce
    1.11
     ecosystem
    1.11
    Activations Density 0.320%

    No Known Activations