© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 12573
    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
    */(
    -0.85
     Azerb
    -0.75
    ritical
    -0.70
    atile
    -0.65
    ¶æ
    -0.64
    uable
    -0.64
    Ò
    -0.63
    ":""},{"
    -0.61
     Seymour
    -0.61
    paren
    -0.61
    POSITIVE LOGITS
    jar
    0.76
     Meadows
    0.74
    eers
    0.72
    ifice
    0.66
     Elephant
    0.66
     Keys
    0.65
     Gardens
    0.63
    iamond
    0.62
    iannopoulos
    0.61
    acea
    0.61
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.