© 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. 9-RES-JB
    11. 18008
    Prev
    Next
    INDEX
    Explanations

    expressions related to personal experiences and reflections

    oai_token-act-pair · gpt-3.5-turbo

    emotionally charged expressions of distress or concern

    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
     Prix
    -0.53
     Hades
    -0.53
    iga
    -0.51
    ategories
    -0.51
     Allied
    -0.50
     Bulldogs
    -0.49
     CRC
    -0.48
     otherwise
    -0.46
    ãĤ´ãĥ³
    -0.46
     CPUs
    -0.45
    POSITIVE LOGITS
    [/
    1.25
     ..."
    1.12
     [/
    1.07
    ,''
    1.02
    ?'
    0.99
    %"
    0.96
     âĢ¦"
    0.92
     âĢ
    0.92
     [
    0.91
    .,"
    0.89
    Activations Density 1.678%

    No Known Activations