© 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. 1-RES-JB
    11. 3866
    Prev
    Next
    INDEX
    Explanations

    phrases related to high levels of fat content

    oai_token-act-pair · gpt-3.5-turbo

    terms related to saturated fat

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stub
    -0.74
    uni
    -0.68
    friend
    -0.66
    atti
    -0.65
     disappro
    -0.62
     Guid
    -0.61
    ľ
    -0.59
    issues
    -0.59
    llor
    -0.58
    bors
    -0.58
    POSITIVE LOGITS
     saturated
    1.11
    aturated
    1.05
    quished
    0.93
     mosqu
    0.84
    ted
    0.81
    omial
    0.81
    ciating
    0.80
    ategory
    0.77
    ivered
    0.77
    elsius
    0.75
    Activations Density 0.012%

    No Known Activations