© 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. 5638
    Prev
    Next
    INDEX
    Explanations

    words related to messiness or disorder

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "mess" and related forms

    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
    vation
    -0.86
    eele
    -0.83
    cember
    -0.81
    undai
    -0.78
    éĸ
    -0.73
    cki
    -0.72
    lux
    -0.71
    HCR
    -0.67
    rendered
    -0.65
     livest
    -0.65
    POSITIVE LOGITS
    engers
    1.67
    iah
    1.25
    enger
    1.24
    aging
    1.10
    aged
    0.99
    ages
    0.97
    iness
    0.94
    INESS
    0.93
    es
    0.88
    alos
    0.84
    Activations Density 0.047%

    No Known Activations