© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 13377
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "OW"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific operational workflows or processes

    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
     circulate
    -0.77
     pinch
    -0.70
    senal
    -0.62
    panic
    -0.61
     è£ıè
    -0.61
     pocket
    -0.59
    utor
    -0.59
     negotiate
    -0.58
     Scand
    -0.58
     forge
    -0.58
    POSITIVE LOGITS
    OW
    1.44
    OWS
    1.31
    IE
    1.13
    LAN
    1.06
    ARDS
    1.06
    ISION
    1.02
    OOD
    1.02
    NN
    1.01
    orld
    1.01
    ITH
    0.98
    Activations Density 0.004%

    No Known Activations