© 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. 3-RES-JB
    11. 17421
    Prev
    Next
    INDEX
    Explanations

    words related to passages or sections within a text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "pass" and its variations, indicating references to passing legislation or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸ī
    -0.78
    AAF
    -0.64
     GOODMAN
    -0.64
     fam
    -0.60
     aber
    -0.58
    aiman
    -0.58
     Cortex
    -0.56
     prospective
    -0.56
    ãĥĸ
    -0.56
    OTAL
    -0.54
    POSITIVE LOGITS
    enger
    1.49
    ioned
    1.37
    ed
    1.18
    engers
    1.16
    ing
    1.14
    es
    1.14
    edIn
    1.08
    pass
    1.05
    ion
    1.05
    wd
    1.01
    Activations Density 0.015%

    No Known Activations