© 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. 1-RES-JB
    11. 20803
    Prev
    Next
    INDEX
    Explanations

    time-related information, specifically relating to hours and minutes in a day

    oai_token-act-pair · gpt-3.5-turbo

    symbols indicating time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ktop
    -0.76
     Vendor
    -0.72
     citiz
    -0.70
    cest
    -0.67
     carniv
    -0.67
    natureconservancy
    -0.66
    */(
    -0.64
    romeda
    -0.64
    ummer
    -0.62
    xual
    -0.62
    POSITIVE LOGITS
    based
    0.71
    hash
    0.69
    obin
    0.69
    iter
    0.69
    exclusive
    0.68
    stop
    0.67
    educated
    0.67
    VALUE
    0.65
    to
    0.65
    rated
    0.64
    Activations Density 0.000%

    No Known Activations