© 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. 9-RES-JB
    6. 22875
    Prev
    Next
    INDEX
    Explanations

    actions involving physical contact between individuals

    oai_token-act-pair · gpt-3.5-turbo

    co-occurring conjunctions and repeated phrases

    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
    etheless
    -0.82
    Correct
    -0.78
    Correction
    -0.77
    relevant
    -0.70
    actionDate
    -0.69
     Presbyter
    -0.68
    nom
    -0.68
    notations
    -0.66
     Improvement
    -0.66
    ander
    -0.66
    POSITIVE LOGITS
     began
    1.11
     gazed
    1.09
     proceeded
    1.06
     stared
    1.05
     waited
    1.01
     exclaimed
    0.99
     whispered
    0.98
     slammed
    0.97
     glared
    0.97
     glanced
    0.95
    Activations Density 0.160%

    No Known Activations