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. 21717
    Prev
    Next
    INDEX
    Explanations

    information related to various topics like capitalism, robotics, politics, and technology

    oai_token-act-pair · gpt-3.5-turbo

    elements related to challenges and constraints

    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
     âĢº
    -0.45
    Copyright
    -0.42
    PRE
    -0.38
    VIDEO
    -0.36
     Copyright
    -0.36
    taboola
    -0.35
     Flavoring
    -0.34
     âĢİ
    -0.34
    Firstly
    -0.34
    Gender
    -0.34
    POSITIVE LOGITS
     however
    0.50
     moreover
    0.48
     meanwhile
    0.48
     though
    0.43
     furthermore
    0.40
     therefore
    0.39
     latter
    0.39
     --------------------
    0.38
    anwhile
    0.38
    ogether
    0.36
    Activations Density 5.958%

    No Known Activations