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

    Neuronpedia

    Jacobian LensNEW
    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. 3-RES-JB
    11. 20529
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of 'ized' or 'ized' as a suffix

    oai_token-act-pair · gpt-3.5-turbo

    terms related to systems or concepts that are 'customized' or 'tailored'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agher
    -0.71
    inness
    -0.70
    idian
    -0.69
    ilan
    -0.69
     Scor
    -0.66
     mate
    -0.66
     ABE
    -0.65
    browser
    -0.64
    haw
    -0.64
    brow
    -0.63
    POSITIVE LOGITS
    ablishment
    0.84
    ouver
    0.81
    orpor
    0.67
    Magikarp
    0.65
    cember
    0.64
    ĨĴ
    0.63
    eer
    0.63
    illance
    0.63
    irect
    0.62
    achusetts
    0.61
    Activations Density 0.036%

    No Known Activations