© 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. 17004
    Prev
    Next
    INDEX
    Explanations

    terms related to individuals' names

    oai_token-act-pair · gpt-3.5-turbo

    words related to names and identifiers

    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
     STATS
    -0.71
     sanity
    -0.69
     envelope
    -0.64
     succession
    -0.62
     Laos
    -0.61
     calming
    -0.60
     sanct
    -0.60
     innocence
    -0.59
     fairness
    -0.59
     preservation
    -0.58
    POSITIVE LOGITS
    oshenko
    1.14
    edo
    1.04
    oval
    1.00
    emouth
    0.90
    asury
    0.89
    arkin
    0.87
    obl
    0.85
    flix
    0.83
    bits
    0.79
    hiba
    0.78
    Activations Density 0.106%

    No Known Activations