© 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. 1-RES-JB
    11. 10393
    Prev
    Next
    INDEX
    Explanations

    phrases related to being on a vehicle or a form of transport

    oai_token-act-pair · gpt-3.5-turbo

    terms related to being "onboard" with something, as well as instances of being "overboard" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    info
    -0.78
    FORE
    -0.77
    coord
    -0.76
    UT
    -0.75
    olds
    -0.73
    _-
    -0.72
    rough
    -0.69
    QB
    -0.68
    Es
    -0.67
    ENS
    -0.67
    POSITIVE LOGITS
     onboard
    1.07
    etooth
    0.89
    unci
    0.87
    emort
    0.86
     impulse
    0.83
    htaking
    0.83
     Cabin
    0.81
     behavi
    0.80
     boarding
    0.78
    isance
    0.76
    Activations Density 0.002%

    No Known Activations