© 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. 23682
    Prev
    Next
    INDEX
    Explanations

    numeric ranges

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe a spectrum or variety of items

    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
    idity
    -0.70
    driving
    -0.68
     brakes
    -0.64
    mit
    -0.64
    win
    -0.64
    iquette
    -0.63
    jug
    -0.62
    talk
    -0.62
    idious
    -0.60
    anasia
    -0.59
    POSITIVE LOGITS
     ranging
    0.98
    Ĥª
    0.93
    ĸļ
    0.92
    ranging
    0.88
    Ń·
    0.78
    abama
    0.76
     Occupations
    0.70
    anned
    0.68
     spanning
    0.67
    ĺħ
    0.67
    Activations Density 0.049%

    No Known Activations