© 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. 16819
    Prev
    Next
    INDEX
    Explanations

    numbers, codes, and technical details

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and specific identifiers

    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
    iful
    -0.85
    ufact
    -0.82
    ointed
    -0.81
    endez
    -0.77
    emade
    -0.74
    ensional
    -0.74
    ugal
    -0.74
    ifully
    -0.73
    inent
    -0.73
     unification
    -0.71
    POSITIVE LOGITS
    MHz
    0.76
    789
    0.74
    RNA
    0.73
     MHz
    0.72
     calories
    0.72
    RF
    0.70
    TW
    0.70
    707
    0.69
    008
    0.69
    RH
    0.69
    Activations Density 0.026%

    No Known Activations