© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 9503
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical cords, wires, or connections

    oai_token-act-pair · gpt-3.5-turbo

    references to "cord" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     IMAGES
    -0.75
    ggies
    -0.66
    iesta
    -0.65
    visible
    -0.62
     Atmosp
    -0.61
     Naz
    -0.59
    hh
    -0.58
    hammad
    -0.58
    ĨĴ
    -0.57
    veyard
    -0.56
    POSITIVE LOGITS
     cord
    1.39
     cords
    0.95
    lessly
    0.90
     Cord
    0.88
    iac
    0.87
    ovan
    0.86
    ret
    0.84
    oba
    0.79
    weed
    0.78
    ages
    0.78
    Activations Density 0.006%

    No Known Activations