© 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 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. 5995
    Prev
    Next
    INDEX
    Explanations

    words related to organizations, entities, and groups

    oai_token-act-pair · gpt-3.5-turbo

    mentions of groups or entities within social or economic contexts

    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
    lier
    -0.71
    rette
    -0.71
    mington
    -0.68
    osate
    -0.64
    ainers
    -0.64
    aneously
    -0.63
    boarding
    -0.62
    obin
    -0.62
    elope
    -0.62
     Chow
    -0.59
    POSITIVE LOGITS
    hip
    1.41
    '
    1.32
    hips
    1.27
    hare
    1.12
    chool
    1.12
    peed
    1.11
    mith
    1.06
    pace
    1.06
    erver
    1.01
    heet
    1.00
    Activations Density 0.274%

    No Known Activations