© 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. 3-RES-JB
    11. 6963
    Prev
    Next
    INDEX
    Explanations

    time-related terms, especially denoting periods of a week or month

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of time references, particularly relating to weeks and months

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uctions
    -0.86
    casts
    -0.72
    ropy
    -0.72
    UCT
    -0.72
    eus
    -0.70
     Flavoring
    -0.68
    ettings
    -0.66
    andals
    -0.65
    inav
    -0.63
     Schwarz
    -0.63
    POSITIVE LOGITS
     ago
    1.22
     Ago
    1.06
     apiece
    0.89
    long
    0.84
     overdue
    0.77
     elapsed
    0.75
    glass
    0.75
    dozen
    0.72
    gap
    0.70
    oshenko
    0.66
    Activations Density 0.189%

    No Known Activations