© 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. 11-RES-JB
    11. 89
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a significant amount of information or knowledge

    oai_token-act-pair · gpt-3.5-turbo

    statements about the state of knowledge or information regarding a subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     IDs
    -0.69
    ounter
    -0.63
    iate
    -0.63
    inately
    -0.62
    erto
    -0.62
    utherland
    -0.61
    frames
    -0.61
     heights
    -0.60
     Shooter
    -0.58
     heels
    -0.58
    POSITIVE LOGITS
     learnt
    0.88
     forgiven
    0.84
    ayers
    0.82
     known
    0.81
     changed
    0.81
     transpired
    0.77
     learned
    0.72
     written
    0.69
     forgotten
    0.69
     gained
    0.67
    Activations Density 0.090%

    No Known Activations