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. 10-RES-JB
    6. 18415
    Prev
    Next
    INDEX
    Explanations

    specific introductory phrases used in text, possibly to catch attention or indicate a transition

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "The"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ò
    -0.72
    ãĥĺ
    -0.68
    rade
    -0.64
    dk
    -0.63
     theirs
    -0.63
    .''
    -0.62
     exceeds
    -0.61
    plet
    -0.61
    .<
    -0.61
    âĵĺ
    -0.61
    POSITIVE LOGITS
    odore
    1.37
     Basics
    1.32
     gist
    1.28
    resa
    1.27
     Problem
    1.26
    oret
    1.23
    ories
    1.17
     simplest
    1.14
     irony
    1.08
    ory
    1.07
    Activations Density 0.313%

    No Known Activations