© 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. 3502
    Prev
    Next
    INDEX
    Explanations

    information related to software updates and launches in the tech industry

    oai_token-act-pair · gpt-3.5-turbo

    references to upcoming software updates or product launches

    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
    nown
    -0.83
    ureau
    -0.83
    ewitness
    -0.80
    licted
    -0.78
     volunteered
    -0.78
    SPONSORED
    -0.76
     versa
    -0.76
    onds
    -0.76
    afety
    -0.75
    orget
    -0.75
    POSITIVE LOGITS
     Xperia
    1.27
     PlayStation
    1.22
     Oculus
    1.21
     Xbox
    1.19
     HTC
    1.19
     OnePlus
    1.18
     Ghostbusters
    1.17
     Xiaomi
    1.17
     indie
    1.12
     GeForce
    1.10
    Activations Density 0.752%

    No Known Activations