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. 933
    Prev
    Next
    INDEX
    Explanations

    adjectives and descriptive phrases

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express a combination of conditions or contexts

    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
    ".
    -0.68
    ";
    -0.63
    "(
    -0.62
    chuk
    -0.61
    opian
    -0.61
    ''.
    -0.61
    }.
    -0.60
    kill
    -0.59
    ombat
    -0.57
    .''
    -0.56
    POSITIVE LOGITS
     congr
    0.64
     apologies
    0.63
     irony
    0.62
     ?)
    0.59
     @
    0.58
     economists
    0.56
     sarc
    0.56
     huh
    0.55
     Bernstein
    0.54
     automakers
    0.54
    Activations Density 2.095%

    No Known Activations