© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1-RES-JB
    11. 10377
    Prev
    Next
    INDEX
    Explanations

    objects associated with storage spaces such as closets or drawers

    oai_token-act-pair · gpt-3.5-turbo

    references to storage spaces such as closets and drawers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Interstitial
    -0.66
    ACA
    -0.63
    slow
    -0.62
    Rich
    -0.61
    aceous
    -0.59
    vati
    -0.58
    ramid
    -0.57
    paying
    -0.57
     Pai
    -0.57
    onso
    -0.57
    POSITIVE LOGITS
     closet
    1.45
    pedia
    0.79
    soDeliveryDate
    0.78
    SpaceEngineers
    0.76
     cabinet
    0.75
    glers
    0.73
    isSpecialOrderable
    0.73
    buster
    0.72
    ysis
    0.71
    bryce
    0.71
    Activations Density 0.006%

    No Known Activations