© 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. 9482
    Prev
    Next
    INDEX
    Explanations

    words related to server management and technology

    oai_token-act-pair · gpt-3.5-turbo

    references to servers and server management

    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
    hya
    -0.84
    itives
    -0.80
    ĸļ
    -0.79
    ition
    -0.78
    itious
    -0.77
    umar
    -0.76
    ible
    -0.75
    itsch
    -0.74
    orical
    -0.74
    ibility
    -0.70
    POSITIVE LOGITS
     overloaded
    0.82
     reception
    0.81
     admins
    0.79
     operated
    0.78
     operating
    0.73
    Deploy
    0.71
     farms
    0.70
     servers
    0.70
    izen
    0.69
     server
    0.69
    Activations Density 0.031%

    No Known Activations