© 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. 6989
    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
    azel
    -0.85
    east
    -0.83
    çīĪ
    -0.82
    £ı
    -0.79
    avascript
    -0.75
    20439
    -0.72
    ikh
    -0.71
    isode
    -0.69
    aroo
    -0.68
    atives
    -0.67
    POSITIVE LOGITS
     detectors
    0.70
     detector
    0.67
     Rowe
    0.66
    ennis
    0.65
     answering
    0.64
     Merrill
    0.62
     scissors
    0.61
     guiActiveUnfocused
    0.61
     constitu
    0.60
    orously
    0.59
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.