© 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. 9-RES-JB
    11. 7311
    Prev
    Next
    INDEX
    Explanations

    words related to challenging or dangerous situations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to challenging or adverse conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yss
    -0.74
    allion
    -0.72
    irlf
    -0.71
    izzle
    -0.66
    orem
    -0.64
    ollower
    -0.63
     plaint
    -0.62
     badge
    -0.61
    ratulations
    -0.61
     guessed
    -0.61
    POSITIVE LOGITS
     circumstances
    1.60
     situations
    1.59
     environments
    1.54
     contexts
    1.49
     climates
    1.27
     surroundings
    1.26
     circumstance
    1.26
     conditions
    1.24
     areas
    1.17
     places
    1.15
    Activations Density 0.291%

    No Known Activations