© 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. 11433
    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
    Pros
    -0.79
    aurus
    -0.74
    chal
    -0.69
     bliss
    -0.69
    osate
    -0.68
    zes
    -0.68
    ãĥ¯
    -0.67
    anan
    -0.66
    udos
    -0.65
    Wr
    -0.65
    POSITIVE LOGITS
     absentee
    0.67
     ILCS
    0.67
     Logged
    0.64
     bullpen
    0.60
     fibers
    0.57
    athi
    0.56
     Weaver
    0.55
     motivate
    0.55
     Camden
    0.54
     deadlines
    0.54
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.