© 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 EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 9957
    Prev
    Next
    INDEX
    Explanations

    terms related to network and computer hardware configurations

    oai_token-act-pair · gpt-3.5-turbo

    technical terms related to networking and data storage protocols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    terday
    -0.87
    erk
    -0.84
    igun
    -0.82
    holm
    -0.79
    itar
    -0.78
    iatus
    -0.77
    esta
    -0.76
    ivan
    -0.76
    nir
    -0.76
    erker
    -0.75
    POSITIVE LOGITS
    TABLE
    0.83
     connectivity
    0.79
     specification
    0.78
     throughput
    0.72
    RFC
    0.72
     connectors
    0.71
     sensitivity
    0.71
     connections
    0.71
    US
    0.69
    API
    0.68
    Activations Density 0.033%

    No Known Activations