© 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. 11498
    Prev
    Next
    INDEX
    Explanations

    phrases relating to the passage of time

    oai_token-act-pair · gpt-3.5-turbo

    the pronoun "it" in various contexts

    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
    cknow
    -0.79
    quartered
    -0.69
    oided
    -0.65
    agogue
    -0.63
     Offer
    -0.59
    detail
    -0.58
    rouse
    -0.57
    ORT
    -0.57
     Explain
    -0.57
     Codec
    -0.57
    POSITIVE LOGITS
     rains
    1.40
     happens
    1.22
     disappears
    1.21
     becomes
    1.21
     explodes
    1.16
     fades
    1.15
     gets
    1.13
     reaches
    1.12
     hurts
    1.12
     sinks
    1.11
    Activations Density 0.163%

    No Known Activations