© 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. 6-RES-JB
    11. 8012
    Prev
    Next
    INDEX
    Explanations

    phrases related to modifications or enhancements

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating accumulation or increase

    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
    anches
    -0.76
    aine
    -0.75
    SPONSORED
    -0.75
    ILA
    -0.72
    oi
    -0.70
    ģĸ
    -0.70
    ORGE
    -0.69
    ommel
    -0.69
    aida
    -0.69
    ...]
    -0.68
    POSITIVE LOGITS
     versions
    0.95
    ness
    0.89
     version
    0.87
     sized
    0.76
    ly
    0.69
     wording
    0.69
     crit
    0.68
     amounts
    0.68
    nes
    0.67
     approach
    0.67
    Activations Density 0.070%

    No Known Activations