© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 17363
    Prev
    Next
    INDEX
    Explanations

    phrases with verbs relating to communication and instructions

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to communication and feedback

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tein
    -0.67
    rouse
    -0.66
    rise
    -0.64
    ources
    -0.63
     Combine
    -0.62
    ajo
    -0.61
    ARE
    -0.59
    Bug
    -0.58
    ours
    -0.58
    Labor
    -0.58
    POSITIVE LOGITS
     aback
    0.89
     psychiat
    0.73
    ivated
    0.67
    itialized
    0.66
    vier
    0.65
    wic
    0.62
    ãĤ¼
    0.61
     condem
    0.61
    hearted
    0.61
    Mich
    0.61
    Activations Density 0.504%

    No Known Activations