© 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. 22575
    Prev
    Next
    INDEX
    Explanations

    phrases related to identification or categorization through the use of an identifier

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "ID" followed by numerical references or identifiers

    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
    andise
    -0.76
     silence
    -0.71
    bilt
    -0.69
     Gamb
    -0.67
     circulation
    -0.67
    uten
    -0.65
     hypot
    -0.65
    ã
    -0.65
     biscuits
    -0.63
     pandemonium
    -0.63
    POSITIVE LOGITS
    irect
    1.19
    iots
    1.11
    ocument
    1.06
    irection
    0.98
    ividual
    0.97
    ID
    0.96
    DEN
    0.95
    iotic
    0.93
    aho
    0.90
    ouble
    0.90
    Activations Density 0.009%

    No Known Activations