© 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. 3-RES-JB
    11. 4172
    Prev
    Next
    INDEX
    Explanations

    dates and related information structured in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    elements related to dates, routes, and schedules

    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
     calendars
    -0.54
    gel
    -0.46
     Ambro
    -0.46
     footwear
    -0.46
     coh
    -0.44
    ãĥŃ
    -0.44
    986
    -0.44
     EDIT
    -0.44
    gra
    -0.43
     Hug
    -0.43
    POSITIVE LOGITS
    )=(
    0.62
    ohm
    0.59
    espie
    0.59
     Wraith
    0.57
    endif
    0.55
    isoft
    0.53
    istani
    0.52
    orea
    0.51
    amiya
    0.50
     targ
    0.50
    Activations Density 1.947%

    No Known Activations