© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 8-RES-JB
    11. 8309
    Prev
    Next
    INDEX
    Explanations

    instances of conditional statements

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements beginning with "if that."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    izens
    -0.79
    greg
    -0.79
    enegger
    -0.76
    ajor
    -0.76
    izont
    -0.72
    ãĤ¸
    -0.72
    ãĥ¯ãĥ³
    -0.70
    onica
    -0.68
    stals
    -0.68
    pots
    -0.68
    POSITIVE LOGITS
     happens
    1.25
     happened
    1.09
     occurs
    1.08
     translates
    1.07
     occurred
    0.90
     applies
    0.90
     entails
    0.90
     sounds
    0.89
     contradicts
    0.88
     happen
    0.88
    Activations Density 0.162%

    No Known Activations