© 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. 10-RES-JB
    11. 13842
    Prev
    Next
    INDEX
    Explanations

    statements indicating negation or opposition

    oai_token-act-pair · gpt-3.5-turbo

    negative phrases or sentiments related to personal experiences and expectations

    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
     Alas
    -0.72
    éŃĶ
    -0.71
    éĹĺ
    -0.70
    ãģ®å
    -0.68
     duly
    -0.68
    TIME
    -0.67
    Dear
    -0.67
    è¦ļéĨĴ
    -0.67
     Must
    -0.66
    ãģ®ç
    -0.65
    POSITIVE LOGITS
     necessarily
    1.24
     anybody
    0.97
     really
    0.96
     gonna
    0.95
     wanna
    0.95
     flashy
    0.95
     anymore
    0.95
     [
    0.89
     everybody
    0.89
     disrespect
    0.85
    Activations Density 0.240%

    No Known Activations