© 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. 10-RES-JB
    11. 6629
    Prev
    Next
    INDEX
    Explanations

    the word "even" occurring within sentences

    oai_token-act-pair · gpt-3.5-turbo

    the word "even."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rend
    -0.82
    aim
    -0.75
    acker
    -0.73
    aser
    -0.70
    arnaev
    -0.70
    notations
    -0.69
    essee
    -0.69
    ãĤ´ãĥ³
    -0.69
    Shape
    -0.67
    ffen
    -0.66
    POSITIVE LOGITS
     though
    1.05
    handedly
    1.03
     tho
    0.98
     remotely
    0.98
    handed
    0.97
     moderately
    0.92
     if
    0.91
     rudimentary
    0.89
     mundane
    0.83
     slightest
    0.83
    Activations Density 0.064%

    No Known Activations