© 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. 13418
    Prev
    Next
    INDEX
    Explanations

    references to specific durations of time, specifically of around one hour

    oai_token-act-pair · gpt-3.5-turbo

    references to durations of time, specifically "hour."

    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
    LECT
    -0.73
    founded
    -0.70
    atro
    -0.69
    ãģį
    -0.66
    ortium
    -0.66
    ãĥķãĤ©
    -0.65
    culture
    -0.63
     Pra
    -0.63
    ashtra
    -0.63
    ãĥ´ãĤ¡
    -0.63
    POSITIVE LOGITS
    glass
    1.23
    endment
    0.92
     mins
    0.85
     hour
    0.84
     Ago
    0.77
    bnb
    0.75
     ILCS
    0.75
     hrs
    0.73
     Hour
    0.71
    ï¸
    0.70
    Activations Density 0.010%

    No Known Activations