© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 7749
    Prev
    Next
    INDEX
    Explanations

    mentions of legal actions or consequences

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ça
    -0.70
    nance
    -0.69
    racuse
    -0.68
    ional
    -0.67
    âĿ
    -0.66
    load
    -0.65
    pointers
    -0.63
    lander
    -0.62
    ometers
    -0.62
    zbollah
    -0.62
    POSITIVE LOGITS
     guise
    1.48
     midst
    1.34
     meantime
    1.21
     hopes
    1.20
     wake
    1.17
     hope
    1.16
     pursuit
    1.15
     vain
    1.13
     manner
    1.11
     absence
    1.10
    Activations Density 0.165%

    No Known Activations