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. 4943
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals or groups involved in specific events

    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
     exception
    -0.74
    JECT
    -0.70
    ctors
    -0.68
    Phys
    -0.64
     divest
    -0.63
    ASED
    -0.63
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.62
     adjunct
    -0.62
    liest
    -0.62
     cleaners
    -0.62
    POSITIVE LOGITS
    ilver
    1.45
    peed
    1.37
    hirt
    1.36
    aurus
    1.33
    omething
    1.24
    creen
    1.23
    mith
    1.19
    hift
    1.18
    hip
    1.17
    pace
    1.17
    Activations Density 0.204%

    No Known Activations