© 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. 14237
    Prev
    Next
    INDEX
    Explanations

    phrases indicating likelihood or probability

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating likelihood or expectation of events

    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
    spection
    -0.71
    assed
    -0.65
     Replacement
    -0.64
    holes
    -0.62
    unes
    -0.62
     Sure
    -0.61
    Library
    -0.60
     Isn
    -0.60
    orno
    -0.60
    pointers
    -0.59
    POSITIVE LOGITS
     intensify
    1.28
     prevail
    1.17
     worsen
    1.17
     emerge
    1.11
     disappoint
    1.11
     exacerbate
    1.11
     reap
    1.09
     elicit
    1.09
     escalate
    1.09
     attract
    1.08
    Activations Density 0.121%

    No Known Activations