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. 17915
    Prev
    Next
    INDEX
    Explanations

    qualifiers emphasizing a certain quality or characteristic

    oai_token-act-pair · gpt-3.5-turbo

    expressions of a sense of moderation or relativity, using the term "kind."

    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
     VIDEOS
    -0.71
    edia
    -0.70
    oulos
    -0.68
    ERY
    -0.68
    è¦ļéĨĴ
    -0.65
    IBLE
    -0.62
    KS
    -0.62
     assailants
    -0.61
    mma
    -0.60
     Minutes
    -0.60
    POSITIVE LOGITS
    ¹
    0.73
    este
    0.70
     Kind
    0.69
    faces
    0.68
     grapes
    0.67
    assy
    0.66
    cast
    0.66
    nered
    0.64
    sort
    0.63
     Whe
    0.62
    Activations Density 0.028%

    No Known Activations