© 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. 3-RES-JB
    6. 1911
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cyp
    -0.82
     retali
    -0.68
     procedural
    -0.64
     Cipher
    -0.64
     Platinum
    -0.63
     Access
    -0.63
    leading
    -0.62
     Celebrity
    -0.62
     Cluster
    -0.60
     Proced
    -0.60
    POSITIVE LOGITS
    ierrez
    0.87
    ashtra
    0.82
    ²¾
    0.78
    ause
    0.77
    redd
    0.75
    ahi
    0.75
    agi
    0.75
    grand
    0.74
    esa
    0.74
    ernal
    0.73
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.