Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 19112
    Prev
    Next
    INDEX
    Explanations

    calls to action and instructions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to engagement and participation in a collaborative process

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     displacement
    -0.83
     acute
    -0.77
    ibur
    -0.71
    acet
    -0.69
     McCoy
    -0.68
     deteriorated
    -0.67
    æŃ¦
    -0.66
    ¥µ
    -0.66
    ideo
    -0.65
     sustained
    -0.65
    POSITIVE LOGITS
     :)
    1.17
     THANK
    1.08
     ;)
    1.08
     Submit
    1.06
     Username
    1.05
    Thank
    1.03
     Donation
    1.02
     :-)
    0.99
     Email
    0.99
     Please
    0.97
    Activations Density 0.581%

    No Known Activations