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. 0-RES-JB
    6. 3442
    Prev
    Next
    INDEX
    Explanations

    references to hemp-related events and initiatives

    oai_token-act-pair · gpt-3.5-turbo

    mentions of hemp

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     behav
    -0.76
    Interstitial
    -0.73
     interacted
    -0.72
     contamin
    -0.67
     sufficiently
    -0.67
    Application
    -0.66
     necessarily
    -0.65
     guiActiveUnfocused
    -0.65
     heating
    -0.64
     irrig
    -0.64
    POSITIVE LOGITS
    ihad
    0.87
    addons
    0.83
     Reloaded
    0.76
    oples
    0.74
    awks
    0.74
    oppable
    0.73
    ackers
    0.73
    netflix
    0.72
    ikk
    0.71
    ool
    0.68
    Activations Density 0.000%

    No Known Activations