© 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. 4-RES-JB
    11. 12239
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences corresponding to the end of documents or sections

    oai_token-act-pair · gpt-3.5-turbo

    various forms of the word "feel" or expressions of emotions

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

    No Comments

    Negative Logits
    raints
    -0.82
    matic
    -0.82
     grips
    -0.78
     primates
    -0.75
     Instr
    -0.74
     restraints
    -0.74
     levers
    -0.73
    ulators
    -0.72
     scissors
    -0.69
     synerg
    -0.68
    POSITIVE LOGITS
    âĶĢâĶĢ
    1.26
    ï¸ı
    1.07
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    1.02
    conom
    0.89
    âĶĢâĶĢâĶĢâĶĢ
    0.88
    Ķ
    0.86
    Ł
    0.85
    fter
    0.84
    Ĩ
    0.84
    İ
    0.84
    Activations Density 0.172%

    No Known Activations