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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6468
    Prev
    Next
    INDEX
    Explanations

    the word "then" in code-like contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "then"

    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
     Bie
    -0.63
     nerve
    -0.61
    toe
    -0.59
    idad
    -0.58
    ting
    -0.57
     Peninsula
    -0.56
    ments
    -0.55
     Jenner
    -0.55
    mission
    -0.55
    pace
    -0.55
    POSITIVE LOGITS
     proceeded
    0.81
    orthy
    0.76
    anski
    0.76
    ©¶æ
    0.74
    ratulations
    0.74
     proceed
    0.74
    EStream
    0.72
    Ń·
    0.71
    daq
    0.69
    adays
    0.69
    Activations Density 0.060%

    No Known Activations