© 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. 10-RES-JB
    11. 4343
    Prev
    Next
    INDEX
    Explanations

    unique identifiers or codes

    oai_token-act-pair · gpt-3.5-turbo

    instances of the identifier "Id" followed by a number

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    toe
    -0.76
     torped
    -0.64
    izations
    -0.64
     Turing
    -0.63
    ĵĺ
    -0.59
     Union
    -0.57
     Silence
    -0.57
     thinner
    -0.57
    peak
    -0.57
    bilt
    -0.57
    POSITIVE LOGITS
    iosyncr
    1.39
    entity
    1.37
    iots
    1.34
    yll
    1.31
    iotic
    1.30
    aho
    1.29
    iom
    1.25
    leness
    1.25
    iop
    1.20
    ividual
    1.20
    Activations Density 0.023%

    No Known Activations