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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3-RES-JB
    11. 10685
    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
    mic
    -0.60
     ber
    -0.58
    mal
    -0.58
     proceeding
    -0.57
     dwelling
    -0.55
    pol
    -0.54
    Dest
    -0.54
    _-
    -0.54
     im
    -0.54
     maj
    -0.53
    POSITIVE LOGITS
    ļéĨĴ
    0.77
    TextColor
    0.72
    xtap
    0.66
    issan
    0.64
    eteenth
    0.64
    perature
    0.63
     Polo
    0.63
    udder
    0.63
    cius
    0.62
     Romeo
    0.61
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.