© 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. 3-RES-JB
    11. 17653
    Prev
    Next
    INDEX
    Explanations

    names of specific locations or organizations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of notable individuals or organizations

    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
    ItemTracker
    -0.72
    quarters
    -0.68
    raising
    -0.67
    onsense
    -0.66
    matically
    -0.64
     nudity
    -0.63
     canopy
    -0.63
    cling
    -0.61
    road
    -0.61
    retty
    -0.61
    POSITIVE LOGITS
    iour
    1.01
    itri
    0.89
     Sev
    0.85
    chenko
    0.82
    ILLE
    0.80
    opol
    0.76
    cha
    0.76
    illa
    0.75
    ius
    0.74
    Ò
    0.74
    Activations Density 0.009%

    No Known Activations