© 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. 12000
    Prev
    Next
    INDEX
    Explanations

    dates and time-related information

    oai_token-act-pair · gpt-3.5-turbo

    the recurring phrase "at the time of" 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
    ply
    -0.78
    fml
    -0.74
    achus
    -0.68
    notations
    -0.67
     ILCS
    -0.66
     WATCHED
    -0.66
    common
    -0.65
    ivably
    -0.65
    æµ
    -0.64
    ãĥĥãĥī
    -0.63
    POSITIVE LOGITS
     publication
    1.22
     enactment
    1.15
     writing
    1.14
     issuance
    1.07
     arrival
    1.06
     inception
    1.06
     conception
    1.05
     departure
    1.02
     publishing
    1.01
     onset
    1.01
    Activations Density 0.130%

    No Known Activations