© 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. 7754
    Prev
    Next
    INDEX
    Explanations

    descriptions of various car features, specifically those related to the rear of the vehicle

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the rear features of vehicles

    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
    âĸĪâĸĪ
    -0.92
    eteria
    -0.87
    ensable
    -0.84
    wana
    -0.82
    âĸĪâĸĪâĸĪâĸĪ
    -0.77
    etus
    -0.77
    âĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪ
    -0.77
    eto
    -0.77
    ciating
    -0.77
    ioxide
    -0.75
    POSITIVE LOGITS
    ward
    1.19
     axle
    1.09
     tyre
    1.05
     bumper
    1.04
     derail
    0.99
    view
    0.97
     wheel
    0.94
    side
    0.93
     lobe
    0.92
     tyres
    0.91
    Activations Density 0.030%

    No Known Activations