© 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. 5422
    Prev
    Next
    INDEX
    Explanations

    adjectives or nouns related to negative events or disasters

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various forms of disaster or catastrophic events

    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
    cius
    -0.89
     facult
    -0.76
     accredited
    -0.72
    soDeliveryDate
    -0.70
    Recomm
    -0.69
     propri
    -0.69
     certific
    -0.68
     supervised
    -0.66
    approved
    -0.66
     complementary
    -0.65
    POSITIVE LOGITS
     havoc
    1.00
     inflicted
    1.00
    bite
    0.85
     devastation
    0.79
     wre
    0.78
     devast
    0.76
     plag
    0.76
     Antar
    0.76
    ous
    0.75
     damage
    0.73
    Activations Density 0.220%

    No Known Activations