© 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. 10-RES-JB
    11. 6597
    Prev
    Next
    INDEX
    Explanations

    devices and measurements in a technological context

    oai_token-act-pair · gpt-3.5-turbo

    references to products or details related to technology and entertainment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Alc
    -0.86
    Asset
    -0.85
     Aber
    -0.81
     Aven
    -0.80
    ahime
    -0.77
     indefinite
    -0.74
     Abstract
    -0.74
     AB
    -0.74
     Iro
    -0.74
     Ald
    -0.73
    POSITIVE LOGITS
    fn
    0.89
    vin
    0.79
    bler
    0.74
    jon
    0.73
    Jon
    0.72
    rpm
    0.70
    pie
    0.69
     Koen
    0.69
    git
    0.69
    lest
    0.68
    Activations Density 0.299%

    No Known Activations