© 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. 3-RES-JB
    11. 677
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a statement of what should occur or what is expected

    oai_token-act-pair · gpt-3.5-turbo

    statements expressing necessity or recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     maze
    -0.73
     opium
    -0.69
    hole
    -0.68
    ories
    -0.68
     Wid
    -0.67
     hostage
    -0.65
     Magnetic
    -0.64
     coma
    -0.64
     Puzzle
    -0.64
     Trails
    -0.64
    POSITIVE LOGITS
    arna
    0.90
    ghai
    0.74
     judged
    0.74
    eele
    0.74
    amation
    0.73
    autions
    0.71
    rifice
    0.69
    arers
    0.68
    erto
    0.68
    cellence
    0.68
    Activations Density 0.183%

    No Known Activations