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. 4434
    Prev
    Next
    INDEX
    Explanations

    the word "else"

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the concept of alternatives or additional options

    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
     testament
    -0.67
    ritz
    -0.58
    shock
    -0.57
    ures
    -0.56
    eme
    -0.52
    opian
    -0.52
     courtesy
    -0.51
    formation
    -0.50
    hardt
    -0.50
    arie
    -0.50
    POSITIVE LOGITS
     else
    3.93
    else
    2.52
    Else
    2.42
     Else
    2.39
     Otherwise
    1.56
    Otherwise
    1.50
     endif
    1.50
    endif
    1.39
     otherwise
    1.35
     alternatively
    1.20
    Activations Density 0.029%

    No Known Activations