Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 21084
    Prev
    Next
    INDEX
    Explanations

    instances where the phrase "don't have" or "doesn't have" is used

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "have" in various contexts

    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
    catentry
    -0.76
    ilation
    -0.73
     guiName
    -0.62
    sequent
    -0.58
    nown
    -0.57
    attery
    -0.56
    patch
    -0.56
     notwithstanding
    -0.55
    PHOTOS
    -0.54
    later
    -0.54
    POSITIVE LOGITS
     been
    0.88
    gotten
    0.79
     necessarily
    0.78
     anymore
    0.76
     gotten
    0.75
     any
    0.75
     enough
    0.75
     anything
    0.73
     seen
    0.73
     bothered
    0.72
    Activations Density 0.061%

    No Known Activations