© 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. 2-RES-JB
    11. 10392
    Prev
    Next
    INDEX
    Explanations

    references to Blu-ray formats

    oai_token-act-pair · gpt-3.5-turbo

    references to Blu-ray discs and their various releases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ERAL
    -0.75
    ILY
    -0.71
    DAY
    -0.70
    ISTORY
    -0.69
     prevailing
    -0.67
    Ö¼
    -0.66
    ablishment
    -0.63
    ammad
    -0.63
    BRE
    -0.62
     equations
    -0.61
    POSITIVE LOGITS
    etooth
    1.32
    ewater
    1.00
    omore
    0.92
    eno
    0.84
     Blu
    0.82
    isl
    0.79
    ridge
    0.79
    issance
    0.79
    eness
    0.78
    estone
    0.78
    Activations Density 0.003%

    No Known Activations