© 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. 17427
    Prev
    Next
    INDEX
    Explanations

    keywords related to the name "Helms"

    oai_token-act-pair · gpt-3.5-turbo

    references to measurements or metrics

    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
     Rican
    -0.72
    OPLE
    -0.66
     Strauss
    -0.65
    ASED
    -0.65
     testimonies
    -0.62
     visceral
    -0.62
     acids
    -0.61
    idates
    -0.61
     millenn
    -0.60
     arcs
    -0.59
    POSITIVE LOGITS
    pace
    1.16
    erver
    1.06
    manship
    1.05
    dn
    1.04
    fw
    0.99
    ettings
    0.92
    creen
    0.92
    cript
    0.92
    gt
    0.91
    achus
    0.91
    Activations Density 0.008%

    No Known Activations