© 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. 0-RES-JB
    6. 10120
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulum
    -0.79
    ji
    -0.78
    rar
    -0.75
    CSS
    -0.71
    ROM
    -0.70
    jl
    -0.70
    PDF
    -0.69
    Äĩ
    -0.67
    TPPStreamerBot
    -0.67
    js
    -0.66
    POSITIVE LOGITS
     intoxication
    0.84
     endanger
    0.77
     depletion
    0.76
     ingred
    0.73
     contribut
    0.73
     incap
    0.72
     poisoning
    0.71
     unnecess
    0.69
     intolerance
    0.69
     intox
    0.68
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.