© 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. 4-RES-JB
    11. 10481
    Prev
    Next
    INDEX
    Explanations

    phrases related to white papers or technical documents

    oai_token-act-pair · gpt-3.5-turbo

    words related to academic or professional papers

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

    No Comments

    Negative Logits
    sie
    -0.76
    ¯
    -0.75
    addin
    -0.71
    s
    -0.65
    ivity
    -0.63
    este
    -0.62
     4090
    -0.61
     Canterbury
    -0.61
    ive
    -0.60
     Kem
    -0.60
    POSITIVE LOGITS
    apers
    1.18
    aper
    1.01
    ILY
    0.97
    ODY
    0.96
    PLIED
    0.82
    flies
    0.81
    IUM
    0.77
    iatrics
    0.77
    clips
    0.75
    ilon
    0.73
    Activations Density 0.016%

    No Known Activations