© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 9203
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     collections
    -0.66
     Grayson
    -0.64
     intrusive
    -0.64
     Poo
    -0.62
     complain
    -0.61
     disabilities
    -0.61
     digit
    -0.61
     delinquent
    -0.57
     Cognitive
    -0.57
    ibrary
    -0.57
    POSITIVE LOGITS
    anism
    0.88
    pez
    0.80
    ramid
    0.79
    jri
    0.79
    upiter
    0.76
    ansson
    0.75
    zsche
    0.74
    tera
    0.74
    thren
    0.73
    WAR
    0.71
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.