© 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. 9-RES-JB
    11. 7348
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific terms or phrases within longer and diverse texts

    oai_token-act-pair · gpt-3.5-turbo

    references to names and notable events or actions

    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
     fortun
    -0.94
     seiz
    -0.89
    ãĤ¦ãĤ¹
    -0.73
     distingu
    -0.71
     sugg
    -0.69
    ifter
    -0.68
    jri
    -0.65
     advoc
    -0.65
     arrang
    -0.64
     compr
    -0.63
    POSITIVE LOGITS
     Banana
    0.83
     Raven
    0.81
     Nin
    0.80
     Kenyan
    0.79
     Raspberry
    0.77
     Nickel
    0.77
     Monte
    0.75
     HRC
    0.75
     Peach
    0.75
     Skydragon
    0.75
    Activations Density 0.692%

    No Known Activations