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. 4-RES-JB
    6. 23942
    Prev
    Next
    INDEX
    Explanations

    file paths

    oai_token-act-pair · gpt-3.5-turbo

    specific file paths or directory structures in a technical context

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

    No Comments

    Negative Logits
     hungry
    -0.67
    jriwal
    -0.67
    usercontent
    -0.63
     Suz
    -0.63
     aloud
    -0.63
     reckoning
    -0.63
     sore
    -0.62
    Initialized
    -0.62
     uncomfortable
    -0.61
     thirsty
    -0.59
    POSITIVE LOGITS
    athan
    0.87
    illa
    0.79
    cade
    0.75
    Ľ
    0.74
    icum
    0.72
    uel
    0.71
    agne
    0.71
    Ļ
    0.71
    ela
    0.70
    idge
    0.70
    Activations Density 0.286%

    No Known Activations