© 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. 2-RES-JB
    11. 11246
    Prev
    Next
    INDEX
    Explanations

    words related to various fields of engineering

    oai_token-act-pair · gpt-3.5-turbo

    terms related to engineering

    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
    ividual
    -0.78
    tle
    -0.74
    cific
    -0.73
     Mub
    -0.71
    vic
    -0.71
    so
    -0.70
    ctuary
    -0.70
    ca
    -0.70
    onymous
    -0.69
    uckle
    -0.69
    POSITIVE LOGITS
     engineering
    1.06
     engineer
    0.92
     jargon
    0.91
     fundamentals
    0.85
     technician
    0.82
     wizard
    0.80
     prowess
    0.80
    rador
    0.77
     specifications
    0.76
     engineers
    0.76
    Activations Density 0.012%

    No Known Activations