© 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. 12839
    Prev
    Next
    INDEX
    Explanations

    phrases related to disorder and confusion

    oai_token-act-pair · gpt-3.5-turbo

    references to chaos in various contexts

    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
    phies
    -0.78
    arers
    -0.78
    icrobial
    -0.74
    missions
    -0.74
    sburgh
    -0.73
    alties
    -0.73
    haps
    -0.72
    ents
    -0.72
    istle
    -0.71
    bors
    -0.70
    POSITIVE LOGITS
     pandemonium
    1.06
     chaos
    1.03
     mayhem
    0.91
     havoc
    0.85
    INESS
    0.84
     ensued
    0.82
     unfold
    0.75
     jams
    0.71
     scramble
    0.69
     eater
    0.68
    Activations Density 0.011%

    No Known Activations