© 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. 6-RES-JB
    11. 9474
    Prev
    Next
    INDEX
    Explanations

    instances of specific objects and actions in a physical setting

    oai_token-act-pair · gpt-3.5-turbo

    items and objects related to everyday life and situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    scape
    -0.53
    Args
    -0.49
    Delivery
    -0.49
    Status
    -0.48
    Population
    -0.47
    Care
    -0.47
    Untitled
    -0.46
    DES
    -0.46
    EVA
    -0.45
    nant
    -0.45
    POSITIVE LOGITS
    mith
    1.07
    heet
    1.05
    hift
    1.04
    hips
    1.03
    hip
    1.02
    creen
    1.00
    pring
    0.97
    uggest
    0.96
    pace
    0.96
    paces
    0.96
    Activations Density 0.740%

    No Known Activations