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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 6044
    Prev
    Next
    INDEX
    Explanations

    phrases related to waiting or ongoing actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that involve continuous action or state while waiting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Christy
    -0.70
     Phelps
    -0.59
     grit
    -0.59
     ..............
    -0.59
    stan
    -0.59
     urgency
    -0.58
     ASAP
    -0.58
     Verse
    -0.58
     quart
    -0.58
    venants
    -0.58
    POSITIVE LOGITS
    imp
    0.73
    olphin
    0.70
     Blaster
    0.67
    amiliar
    0.65
    uble
    0.64
    ebus
    0.64
    angering
    0.63
    eating
    0.62
    REM
    0.62
    utical
    0.61
    Activations Density 0.112%

    No Known Activations