© 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. 3-RES-JB
    11. 9698
    Prev
    Next
    INDEX
    Explanations

    terms related to self-driving vehicles

    oai_token-act-pair · gpt-3.5-turbo

    terms related to self-driving technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é¾įåĸļ士
    -0.85
     Seym
    -0.75
    ings
    -0.74
    ulet
    -0.73
    lain
    -0.73
    NT
    -0.71
    çĦ
    -0.70
    cms
    -0.69
     Neh
    -0.68
    âĿ
    -0.68
    POSITIVE LOGITS
    driving
    0.93
     simulator
    0.85
     mechanic
    0.82
     cars
    0.74
     driving
    0.72
     algorithms
    0.72
     robotic
    0.71
     buggy
    0.71
     bots
    0.70
     braking
    0.69
    Activations Density 0.011%

    No Known Activations