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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6-RES-JB
    6. 8487
    Prev
    Next
    INDEX
    Explanations

    occurrences of a particular symbol or phrase, "

    oai_token-act-pair · gpt-3.5-turbo

    the end of a document or section breaks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     eleph
    -0.72
     reper
    -0.70
     tradem
    -0.65
     circulation
    -0.63
     rushes
    -0.62
     withdrawal
    -0.61
     deposit
    -0.61
     forks
    -0.60
     estranged
    -0.60
     interven
    -0.60
    POSITIVE LOGITS
    WASHINGTON
    1.16
    Abstract
    1.13
    CLOSE
    1.13
    Description
    1.08
    Untitled
    1.07
    Overview
    1.05
    Still
    1.05
    CTV
    1.03
    Trivia
    1.00
    Breaking
    1.00
    Activations Density 0.118%

    No Known Activations