© 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. 11-RES-JB
    11. 14903
    Prev
    Next
    INDEX
    Explanations

    phrases related to completion or conclusion

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "over" used in various contexts and discussions

    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
    esm
    -0.76
     deviations
    -0.66
     deviation
    -0.63
     UD
    -0.59
    DERR
    -0.59
     exceptions
    -0.58
     thereof
    -0.58
     anten
    -0.56
     Cind
    -0.56
     Deity
    -0.55
    POSITIVE LOGITS
    blown
    1.27
    rated
    1.24
    stated
    1.20
    kill
    1.09
    valued
    1.08
    joy
    1.07
    played
    1.07
    priced
    1.06
    sold
    1.06
    due
    1.06
    Activations Density 0.036%

    No Known Activations