© 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. 1-RES-JB
    6. 3826
    Prev
    Next
    INDEX
    Explanations

    special characters

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the registered trademark symbol (®)

    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
    sonian
    -1.03
    ebus
    -0.93
    ynthesis
    -0.80
    ngth
    -0.70
    sburg
    -0.69
     RTX
    -0.68
    ifice
    -0.68
    esters
    -0.68
    arton
    -0.68
    psey
    -0.66
    POSITIVE LOGITS
    ®
    1.55
    âĶĢâĶĢ
    1.25
    âĶĢâĶĢâĶĢâĶĢ
    1.09
    ा
    1.08
    âĶĢ
    1.06
    ر
    1.04
    º
    1.01
    ت
    1.00
    ب
    1.00
    Ùİ
    0.99
    Activations Density 0.003%

    No Known Activations