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. 22956
    Prev
    Next
    INDEX
    Explanations

    quotations or dialogue in a casual setting

    oai_token-act-pair · gpt-3.5-turbo

    conversational and expressive phrases indicating humor or banter

    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
    ".[
    -0.49
    ).[
    -0.45
    ]."
    -0.44
    bryce
    -0.43
    )).
    -0.43
    ."[
    -0.42
    ".
    -0.41
    ?".
    -0.40
    ''.
    -0.38
    !".
    -0.38
    POSITIVE LOGITS
    itialized
    0.43
     Canaver
    0.41
    ADRA
    0.40
     Debor
    0.37
     explanations
    0.37
     Spoiler
    0.37
     Whitman
    0.36
     Carly
    0.35
    ITNESS
    0.35
     glim
    0.34
    Activations Density 6.835%

    No Known Activations