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. 8190
    Prev
    Next
    INDEX
    Explanations

    names related to the name "Ed"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Ed."

    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
    ¬¼
    -0.73
    Ĥİ
    -0.70
    falls
    -0.66
    =-=-
    -0.65
     shotguns
    -0.63
    OWER
    -0.62
    TY
    -0.62
    cffffcc
    -0.61
    INESS
    -0.60
    EStreamFrame
    -0.60
    POSITIVE LOGITS
    gew
    1.12
    dy
    1.10
    mund
    1.10
    itions
    1.07
    ifice
    1.05
    monton
    1.05
    monds
    1.03
    uce
    1.01
    ges
    1.00
    ricks
    0.99
    Activations Density 0.009%

    No Known Activations