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. 7-RES-JB
    6. 903
    Prev
    Next
    INDEX
    Explanations

    statements or descriptions of various current events and their impact

    oai_token-act-pair · gpt-3.5-turbo

    statements asserting the status or condition of various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Telesc
    -0.85
     glances
    -0.71
     senses
    -0.68
     Ends
    -0.68
     yells
    -0.68
    ees
    -0.67
     Clarks
    -0.65
     Isles
    -0.65
     shouts
    -0.65
     encounters
    -0.64
    POSITIVE LOGITS
     currently
    1.18
     unlikely
    1.07
     likely
    1.06
     poised
    1.04
     now
    1.03
    cedented
    0.99
    rael
    0.99
     presently
    0.99
     slated
    0.99
    senal
    0.97
    Activations Density 0.526%

    No Known Activations