© 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. 1-RES-JB
    6. 14344
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     envelope
    -0.73
     subtitle
    -0.70
     perpetrator
    -0.70
     ransom
    -0.69
     toxin
    -0.68
     saturation
    -0.67
     mandate
    -0.67
     landslide
    -0.65
     border
    -0.65
     magically
    -0.65
    POSITIVE LOGITS
    NAS
    0.82
     Gohan
    0.78
    nesota
    0.76
    GGGGGGGG
    0.75
     NEO
    0.73
    ãĤ¯
    0.70
     Rudolph
    0.69
    çĦ
    0.69
    ÏĤ
    0.69
    ammad
    0.68
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.