© 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. 20109
    Prev
    Next
    INDEX
    Explanations

    keywords related to foundational concepts or starting points

    oai_token-act-pair · gpt-3.5-turbo

    references to baseline measurements and snapshots in data analysis contexts

    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
    oth
    -0.73
    oping
    -0.71
    frey
    -0.71
    uild
    -0.71
    phan
    -0.70
    afia
    -0.70
    atom
    -0.69
    omed
    -0.69
    omer
    -0.69
    ousel
    -0.68
    POSITIVE LOGITS
     baseline
    0.85
    tenance
    0.79
    phrine
    0.77
     erosion
    0.75
     measures
    0.72
    gradient
    0.72
     outline
    0.72
     jumper
    0.70
     dummy
    0.70
     characteristics
    0.68
    Activations Density 0.008%

    No Known Activations