© 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. 2-RES-JB
    11. 20649
    Prev
    Next
    INDEX
    Explanations

    mentions of situations or conditions being described as extreme

    oai_token-act-pair · gpt-3.5-turbo

    references to extreme conditions or situations

    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
    ËĪ
    -0.82
    gin
    -0.79
    shaw
    -0.79
    nance
    -0.79
    tein
    -0.77
    morrow
    -0.75
    glas
    -0.75
    bats
    -0.74
    edin
    -0.73
    chel
    -0.73
    POSITIVE LOGITS
     extremes
    1.01
     extreme
    0.97
     lengths
    0.87
     temperatures
    0.78
     rarity
    0.78
     Extreme
    0.78
     instances
    0.77
     punishment
    0.74
    Extreme
    0.74
     punishments
    0.74
    Activations Density 0.009%

    No Known Activations