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. 3-RES-JB
    6. 14927
    Prev
    Next
    INDEX
    Explanations

    dates in the month of August

    oai_token-act-pair · gpt-3.5-turbo

    dates, specifically in August

    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
    OGR
    -0.75
    arantine
    -0.68
     bottleneck
    -0.67
     unfor
    -0.67
    éĹĺ
    -0.62
    IDES
    -0.61
     charged
    -0.61
     NIC
    -0.60
    Interstitial
    -0.60
    aker
    -0.59
    POSITIVE LOGITS
    Aug
    1.08
    mented
    1.07
     Aug
    1.05
    mentation
    0.96
    enture
    0.92
     Feb
    0.86
    sburg
    0.86
    burn
    0.86
    Feb
    0.82
     2021
    0.81
    Activations Density 0.009%

    No Known Activations