© 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. 2-RES-JB
    11. 391
    Prev
    Next
    INDEX
    Explanations

    instances of the word "names."

    oai_token-act-pair · gpt-4-turbo

    names or labels

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the word "names."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yrinth
    -0.71
    irth
    -0.70
     Bed
    -0.69
    OPLE
    -0.67
     Yar
    -0.66
     Smy
    -0.65
    romy
    -0.64
    UGE
    -0.62
     Forestry
    -0.62
    idth
    -0.61
    POSITIVE LOGITS
    paces
    1.58
    pace
    1.10
     names
    1.04
    plates
    1.01
     aliases
    1.01
    paced
    0.96
    ames
    0.96
    hips
    0.92
    akes
    0.91
    names
    0.88
    Activations Density 0.015%

    No Known Activations