© 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. 2-RES-JB
    11. 9228
    Prev
    Next
    INDEX
    Explanations

    phrases related to the term "Extreme"

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Extreme" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     externalToEVAOnly
    -0.74
     Ellison
    -0.71
    ifice
    -0.71
    rooms
    -0.70
    çĦ
    -0.68
    ãģ®éŃĶ
    -0.68
    olith
    -0.67
    externalActionCode
    -0.67
     Io
    -0.66
     rh
    -0.65
    POSITIVE LOGITS
    Extreme
    1.12
     Extreme
    1.01
    aire
    0.78
    visor
    0.78
    erate
    0.74
     Enhancement
    0.72
    entimes
    0.71
    ly
    0.71
     Extrem
    0.71
    ateur
    0.71
    Activations Density 0.016%

    No Known Activations