Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 8187
    Prev
    Next
    INDEX
    Explanations

    words related to self-driving technology and software, specifically mentioning the system "Autopilot."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to autonomous driving technology

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

    No Comments

    Negative Logits
    roots
    -0.69
     spat
    -0.67
    grave
    -0.67
    ĸļ
    -0.67
     kindred
    -0.66
    ################################
    -0.65
     veil
    -0.62
     wid
    -0.62
    é¾įå¥ij士
    -0.62
     orphans
    -0.61
    POSITIVE LOGITS
    PDATE
    0.84
    rencies
    0.83
    nesota
    0.80
    oice
    0.75
    obiles
    0.74
    uggest
    0.71
    ufact
    0.70
    escription
    0.70
    oute
    0.69
    NECT
    0.69
    Activations Density 0.100%

    No Known Activations