© 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. 4-RES-JB
    11. 444
    Prev
    Next
    INDEX
    Explanations

    mentions of natural disasters, specifically droughts

    oai_token-act-pair · gpt-3.5-turbo

    references to drought situations and conditions

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

    No Comments

    Negative Logits
    */(
    -0.99
    ablishment
    -0.90
    ellation
    -0.82
    tein
    -0.77
    roup
    -0.76
    imentary
    -0.72
    ramid
    -0.72
    reme
    -0.71
    irlf
    -0.71
    raltar
    -0.71
    POSITIVE LOGITS
     drought
    1.12
     tolerant
    0.83
    bows
    0.80
    interrupted
    0.78
    lings
    0.76
     famine
    0.75
     worsened
    0.73
     retard
    0.71
    forest
    0.70
    bling
    0.68
    Activations Density 0.011%

    No Known Activations