© 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. 11-RES-JB
    11. 21169
    Prev
    Next
    INDEX
    Explanations

    words related to achieving or obtaining something

    oai_token-act-pair · gpt-3.5-turbo

    terms related to obtaining or achieving something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    ãĤ§
    -0.78
    matter
    -0.77
    sin
    -0.72
    ãĥ¼ãĤ¯
    -0.70
    é»Ĵ
    -0.69
     Stress
    -0.69
    hesis
    -0.65
    +,
    -0.65
    psc
    -0.65
    example
    -0.64
    POSITIVE LOGITS
     permission
    1.28
     approval
    1.14
     visas
    1.11
     permits
    1.10
     approvals
    1.10
     authorization
    1.04
     favourable
    1.04
     clearance
    1.02
     endorsements
    1.00
     acceptance
    0.99
    Activations Density 0.257%

    No Known Activations