© 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. 9250
    Prev
    Next
    INDEX
    Explanations

    references to 360-degree content

    oai_token-act-pair · gpt-3.5-turbo

    references to 360-degree views and experiences

    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
    geist
    -0.89
    nell
    -0.85
    lines
    -0.77
    ality
    -0.76
    enance
    -0.74
    line
    -0.74
    minist
    -0.73
    swick
    -0.73
    itism
    -0.72
    kov
    -0.72
    POSITIVE LOGITS
    °
    1.06
     degrees
    0.96
     Deg
    0.77
     Degree
    0.77
    º
    0.75
     360
    0.70
    deg
    0.70
     deg
    0.66
     Kinect
    0.61
     degree
    0.58
    Activations Density 0.017%

    No Known Activations