Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 625
    Prev
    Next
    INDEX
    Explanations

    time durations expressed in minutes

    oai_token-act-pair · gpt-3.5-turbo

    quantities and cooking times related to food preparation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abase
    -0.63
     mockery
    -0.62
     irony
    -0.60
    ãĥ¯ãĥ³
    -0.60
     Nord
    -0.58
     vanity
    -0.57
    efeated
    -0.57
    adeon
    -0.57
     rhet
    -0.57
     disband
    -0.56
    POSITIVE LOGITS
     minutes
    1.41
     mins
    1.33
    mins
    1.20
     hrs
    1.15
     seconds
    1.06
    seconds
    1.03
     hours
    1.02
     Minutes
    1.00
     min
    0.96
     minute
    0.96
    Activations Density 0.035%

    No Known Activations