© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6187
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate assistance or guidance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    action words related to providing assistance or improvement

    oai_token-act-pair · gpt-3.5-turbo
    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
    Pict
    -0.76
    é¾
    -0.75
    War
    -0.66
    meat
    -0.65
    gran
    -0.64
    ebook
    -0.63
    ols
    -0.62
    Sold
    -0.61
    aval
    -0.61
    ross
    -0.61
    POSITIVE LOGITS
    fully
    0.99
     Desk
    0.84
     facilitate
    0.83
    heet
    0.74
     alleviate
    0.72
    Desk
    0.71
    enza
    0.70
     improve
    0.69
     Assist
    0.67
    meet
    0.67
    Activations Density 0.051%

    No Known Activations