© 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. 10352
    Prev
    Next
    INDEX
    Explanations

    the word "rie" with varying activation strengths

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Berie" in various contexts

    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
    idious
    -0.82
    iop
    -0.78
    tnc
    -0.72
    rity
    -0.71
    imir
    -0.69
    agnetic
    -0.69
    ional
    -0.67
    agons
    -0.66
    worldly
    -0.66
    iary
    -0.65
    POSITIVE LOGITS
    rie
    1.03
    vre
    0.99
    ves
    0.93
    ve
    0.85
    bers
    0.82
    ving
    0.82
    ptions
    0.82
    pton
    0.81
    zo
    0.80
    bs
    0.80
    Activations Density 0.007%

    No Known Activations