© 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. 13305
    Prev
    Next
    INDEX
    Explanations

    computer jargon or technical terms

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases that relate to spirited or animated discussions and interests

    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
    xus
    -1.02
    urden
    -0.90
    ecause
    -0.87
    etheless
    -0.84
    conn
    -0.83
    merce
    -0.81
    handled
    -0.76
    handle
    -0.75
    stru
    -0.72
    lucent
    -0.72
    POSITIVE LOGITS
    natureconservancy
    0.84
    rawdownloadcloneembedreportprint
    0.71
    Examples
    0.69
    RNA
    0.68
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    0.67
    âĶĢâĶĢâĶĢâĶĢ
    0.65
     Yard
    0.65
     Anchorage
    0.64
    ansk
    0.64
    vation
    0.64
    Activations Density 0.026%

    No Known Activations