© 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. 6-RES-JB
    11. 5060
    Prev
    Next
    INDEX
    Explanations

    terms related to the verb "stave", which often signifies prevention or avoidance of something negative

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word 'st' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    merce
    -0.84
    EStream
    -0.82
    hower
    -0.77
    ļéĨĴ
    -0.75
     chronological
    -0.69
     carriers
    -0.68
    éĹĺ
    -0.67
     GOODMAN
    -0.65
    ptive
    -0.64
     Republic
    -0.64
    POSITIVE LOGITS
    uffed
    1.26
    amped
    1.16
    aves
    1.15
    roller
    1.15
    atted
    1.10
    amps
    1.10
    inging
    1.08
    ashing
    1.06
    alker
    1.05
    itched
    1.05
    Activations Density 0.019%

    No Known Activations