© 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. 7-RES-JB
    11. 23508
    Prev
    Next
    INDEX
    Explanations

    adjectives/nouns or verb phrases that suggest something is required or crucial

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "necessary."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awar
    -0.85
    quer
    -0.78
    geon
    -0.78
    elled
    -0.76
    dust
    -0.73
    ahar
    -0.73
    essee
    -0.73
    imore
    -0.72
    emark
    -0.72
    vironment
    -0.72
    POSITIVE LOGITS
     precautions
    0.87
     prec
    0.80
     introdu
    0.78
     precaution
    0.77
     necessities
    0.76
     prerequisite
    0.76
     ingredient
    0.75
     supplies
    0.73
     corrective
    0.72
     redund
    0.70
    Activations Density 0.034%

    No Known Activations