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. 10-RES-JB
    6. 10936
    Prev
    Next
    INDEX
    Explanations

    terms related to cannabis and its derivatives

    oai_token-act-pair · gpt-3.5-turbo

    words associated with food and beverages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     scient
    -0.66
    place
    -0.65
    MIT
    -0.64
     reckoning
    -0.63
     whistlebl
    -0.62
    doi
    -0.60
     Targ
    -0.59
     Shap
    -0.58
     Hitman
    -0.58
     EFF
    -0.57
    POSITIVE LOGITS
    acci
    1.01
    ieri
    0.90
    ainer
    0.90
    ino
    0.88
    imon
    0.87
    ido
    0.86
    ulo
    0.86
    ello
    0.84
    oji
    0.84
    uese
    0.83
    Activations Density 0.129%

    No Known Activations