© 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. 12-RES-JB
    11. 3329
    Prev
    Next
    INDEX
    Explanations

    phrases related to skills or abilities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    expressions of ability or permission

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    ñ
    -0.88
    DeliveryDate
    -0.85
    ò
    -0.84
    PDATE
    -0.83
     practition
    -0.83
    ThumbnailImage
    -0.83
    ġ
    -0.82
    ActionCode
    -0.82
    Ė
    -0.82
    ü
    -0.81
    POSITIVE LOGITS
    't
    1.27
     imagine
    1.02
     argue
    1.02
     bet
    1.02
     hardly
    0.92
     always
    0.91
     easily
    0.91
     probably
    0.89
     tell
    0.88
     certainly
    0.88
    Activations Density 0.131%

    No Known Activations