© 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. 13627
    Prev
    Next
    INDEX
    Explanations

    phrases indicating restriction or limitation

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating exclusivity or restrictions related to specific groups or contexts

    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
    etheless
    -0.75
    asc
    -0.74
    acter
    -0.74
    esh
    -0.73
    plus
    -0.69
    christ
    -0.68
    assi
    -0.67
    fortunately
    -0.65
     syndrome
    -0.62
    inker
    -0.61
    POSITIVE LOGITS
    arde
    0.73
     cosmetic
    0.72
     females
    0.69
     males
    0.68
     aesthetic
    0.68
     superficial
    0.66
     geographic
    0.64
     geographical
    0.64
     aesthetics
    0.63
     areas
    0.63
    Activations Density 0.319%

    No Known Activations