© 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. 9-RES-JB
    11. 5924
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or decisions taken in place of others

    oai_token-act-pair · gpt-3.5-turbo

    instances of alternatives, substitutions, or changes in plans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     >=
    -0.69
    NOT
    -0.67
    ilty
    -0.67
     unavailable
    -0.65
     disagrees
    -0.61
    not
    -0.60
    enegger
    -0.58
    counter
    -0.58
    ieth
    -0.57
     NOT
    -0.57
    POSITIVE LOGITS
    Instead
    1.03
     Instead
    0.91
    ocused
    0.87
     concentrate
    0.84
     focus
    0.81
     focusing
    0.76
    instead
    0.76
     focused
    0.75
     opted
    0.75
    NetMessage
    0.74
    Activations Density 0.184%

    No Known Activations