© 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. 2442
    Prev
    Next
    INDEX
    Explanations

    references to machine parts and components

    oai_token-act-pair · gpt-3.5-turbo

    references to various components or pieces in a mechanical or technical context

    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
    opa
    -0.74
    veyard
    -0.73
    idav
    -0.71
    ternity
    -0.70
    noon
    -0.67
    Syrian
    -0.65
     appropri
    -0.64
    ghan
    -0.64
    antha
    -0.64
    agog
    -0.63
    POSITIVE LOGITS
     datas
    0.83
     kit
    0.80
    units
    0.79
    afety
    0.78
    ridges
    0.78
     Parts
    0.78
    oxy
    0.75
     supplier
    0.75
    icles
    0.73
    icle
    0.71
    Activations Density 0.030%

    No Known Activations