© 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. 4-RES-JB
    11. 16657
    Prev
    Next
    INDEX
    Explanations

    references to custom products or services

    oai_token-act-pair · gpt-3.5-turbo

    references to custom products or services

    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
    hered
    -0.75
    cules
    -0.70
    EGA
    -0.69
     NOTICE
    -0.69
     Scotia
    -0.67
    anners
    -0.66
    OE
    -0.63
    ngth
    -0.62
    ULTS
    -0.62
     Lauder
    -0.60
    POSITIVE LOGITS
    ers
    2.01
    ership
    1.96
    er
    1.83
    erness
    1.08
    erate
    1.07
    ering
    1.05
    ered
    1.02
    ern
    1.01
    eros
    0.98
    ER
    0.96
    Activations Density 0.068%

    No Known Activations