© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 11372
    Prev
    Next
    INDEX
    Explanations

    phrases related to chaotic, intense, and agitated situations or events

    oai_token-act-pair · gpt-3.5-turbo

    terms related to chaotic or intense situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arer
    -0.90
    gemony
    -0.85
    ĻĤ
    -0.81
    arers
    -0.75
    mine
    -0.74
     reused
    -0.73
    roma
    -0.72
    nants
    -0.71
    adra
    -0.70
    ela
    -0.70
    POSITIVE LOGITS
     frenzy
    1.11
     uproar
    0.94
    cffff
    0.90
     hysteria
    0.88
     ILCS
    0.87
     flurry
    0.84
     hyster
    0.83
     pandemonium
    0.81
    wcs
    0.79
     fury
    0.78
    Activations Density 0.030%

    No Known Activations