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. 5623
    Prev
    Next
    INDEX
    Explanations

    phrases related to accepting or rejecting something

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to acceptance or taking responsibility

    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
     glands
    -0.70
    borgh
    -0.69
    bone
    -0.69
    FTWARE
    -0.66
    ixt
    -0.65
     afore
    -0.64
    ooming
    -0.63
     Anthem
    -0.63
    etsk
    -0.62
    ffield
    -0.62
    POSITIVE LOGITS
    ably
    0.91
     accept
    0.89
     accepting
    0.86
    ances
    0.80
    prises
    0.78
    ibles
    0.77
     acceptance
    0.76
    Ĥª
    0.75
     ($)
    0.74
    ardless
    0.74
    Activations Density 0.021%

    No Known Activations