© 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. 411
    Prev
    Next
    INDEX
    Explanations

    instances of text written in Spanish

    oai_token-act-pair · gpt-3.5-turbo

    terms related to appropriateness and classification

    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
     Cheong
    -0.67
     Kiw
    -0.62
    fork
    -0.60
     Valkyrie
    -0.60
     menstrual
    -0.59
     Hollow
    -0.59
    bye
    -0.58
    church
    -0.58
    BuyableInstoreAndOnline
    -0.57
    stead
    -0.57
    POSITIVE LOGITS
    hement
    1.11
    ciating
    1.09
    ities
    1.06
    urity
    1.04
    rities
    1.01
    ibly
    1.00
    eness
    0.95
    enment
    0.94
    tions
    0.94
    ement
    0.91
    Activations Density 0.233%

    No Known Activations