© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 10-RES-JB
    11. 5857
    Prev
    Next
    INDEX
    Explanations

    mentions of high definition technology

    oai_token-act-pair · gpt-3.5-turbo

    references to high-definition (HD) technology and video quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ingen
    -0.99
    notations
    -0.83
    hift
    -0.81
    ortium
    -0.74
    =-=-
    -0.71
    enegger
    -0.71
    oner
    -0.70
    soDeliveryDate
    -0.68
    etta
    -0.68
    ococ
    -0.66
    POSITIVE LOGITS
    TV
    1.15
    PE
    1.05
    Ds
    1.05
    CP
    0.99
    RI
    0.89
    VI
    0.88
    HR
    0.87
    FS
    0.87
    V
    0.81
    VD
    0.81
    Activations Density 0.022%

    No Known Activations