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. 11-RES-JB
    6. 18386
    Prev
    Next
    INDEX
    Explanations

    words related to technical references or specifications

    oai_token-act-pair · gpt-3.5-turbo

    variations of conjunctions and their usage in contexts involving choices or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tackle
    -0.68
    velt
    -0.65
     Seym
    -0.64
    WARD
    -0.62
    robat
    -0.62
    angle
    -0.62
     Britt
    -0.61
    asonic
    -0.60
     Heist
    -0.59
    rance
    -0.59
    POSITIVE LOGITS
     inactive
    1.73
     unavailable
    1.60
     ineligible
    1.48
     unused
    1.44
     dormant
    1.42
     expired
    1.39
     withdrawn
    1.37
     unde
    1.34
     unre
    1.33
     deceased
    1.32
    Activations Density 0.520%

    No Known Activations