© 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. 0-RES-JB
    6. 12073
    Prev
    Next
    INDEX
    Explanations

    positive attributes or qualities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "excellent."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wipes
    -0.73
    strap
    -0.63
    ache
    -0.63
    ivism
    -0.63
    ney
    -0.61
    alties
    -0.59
    ality
    -0.59
    stro
    -0.59
    UTERS
    -0.57
    neys
    -0.57
    POSITIVE LOGITS
     excellent
    3.28
    Excellent
    2.14
     Excellent
    2.14
     terrific
    2.05
     superb
    2.04
     fantastic
    1.94
     wonderful
    1.90
    cellent
    1.86
     admirable
    1.81
     splendid
    1.76
    Activations Density 0.026%

    No Known Activations