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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-RES-JB
    6. 9754
    Prev
    Next
    INDEX
    Explanations

    adjectives describing high intensity or extremeness

    oai_token-act-pair · gpt-3.5-turbo

    extreme adjectives that describe conditions or situations

    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
    Ô
    -0.65
    cember
    -0.59
    zsche
    -0.59
     Brief
    -0.54
    chieve
    -0.53
    ighth
    -0.53
    ilan
    -0.52
     livest
    -0.52
    ãĤ´ãĥ³
    -0.51
    Vert
    -0.50
    POSITIVE LOGITS
     that
    1.40
    that
    1.24
     THAT
    1.04
     it
    0.94
     they
    0.90
    That
    0.90
     That
    0.86
     thats
    0.83
    they
    0.75
     you
    0.70
    Activations Density 0.144%

    No Known Activations