© 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. 8-RES-JB
    11. 2196
    Prev
    Next
    INDEX
    Explanations

    instances of the word "lost" and phrases indicating something being lost or misplaced

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "lost" and related phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    INO
    -0.68
    WIN
    -0.67
    ICAN
    -0.65
    BALL
    -0.64
    Reviewer
    -0.64
     personally
    -0.63
    GF
    -0.62
    CVE
    -0.62
     CLIENT
    -0.62
     empowered
    -0.61
    POSITIVE LOGITS
     obscurity
    1.22
     shuffle
    1.00
     attrition
    0.89
     abstraction
    0.73
     Niet
    0.73
     landsl
    0.73
     clutter
    0.73
     confusion
    0.73
     fog
    0.73
     sands
    0.73
    Activations Density 0.254%

    No Known Activations