© 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. 1872
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a time period or timeline

    oai_token-act-pair · gpt-3.5-turbo

    time-based phrases indicating waiting or delays

    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
    rather
    -0.69
    ãĤ·
    -0.69
    VIDEO
    -0.69
    sequence
    -0.68
    hai
    -0.67
    JV
    -0.67
    unit
    -0.67
    aren
    -0.65
    MOD
    -0.65
    ĺ
    -0.65
    POSITIVE LOGITS
     encountering
    0.95
     anyone
    0.94
     deciding
    0.93
     returning
    0.88
     reaching
    0.87
     seeing
    0.81
     anybody
    0.80
     succ
    0.80
     we
    0.80
     proceeding
    0.80
    Activations Density 0.062%

    No Known Activations