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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 9-RES-JB
    6. 12715
    Prev
    Next
    INDEX
    Explanations

    time durations such as 'weeks' and 'months'

    oai_token-act-pair · gpt-3.5-turbo

    references to time periods related to pregnancy and gestation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inav
    -0.81
    anooga
    -0.65
     Haram
    -0.64
    uria
    -0.62
     hypocr
    -0.62
    inite
    -0.61
     VIDEOS
    -0.61
    ishes
    -0.60
    oos
    -0.59
     ra
    -0.58
    POSITIVE LOGITS
     ago
    1.26
    '
    0.96
    pring
    0.94
     gestation
    0.94
     pregnant
    0.93
     Ago
    0.91
    hips
    0.91
    ago
    0.82
    hift
    0.81
     elapsed
    0.80
    Activations Density 0.108%

    No Known Activations