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

    Neuronpedia

    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. 11-RES-JB
    11. 18603
    Prev
    Next
    INDEX
    Explanations

    phrases related to time progression

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating subjective evaluations or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -0.73
    interstitial
    -0.70
    èĪ
    -0.66
    ij士
    -0.63
    ãĥĹ
    -0.62
    ãĤ£
    -0.62
    ĸļ士
    -0.61
    ©¶æ
    -0.60
    ¿½
    -0.59
    ãĥ©ãĥ³
    -0.58
    POSITIVE LOGITS
     haha
    1.47
     ;)
    1.46
     :)
    1.44
     anyways
    1.41
     lol
    1.37
     tho
    1.33
     :(
    1.33
     :-)
    1.25
    )?
    1.19
     anyway
    1.18
    Activations Density 0.689%

    No Known Activations