© 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. 1-RES-JB
    11. 23551
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esome
    -0.80
    iami
    -0.73
    hester
    -0.72
    claimer
    -0.69
    hett
    -0.67
    interface
    -0.65
    ité
    -0.65
    iety
    -0.65
    idd
    -0.65
    eme
    -0.65
    POSITIVE LOGITS
     sway
    0.67
     rumours
    0.59
     irregularities
    0.58
     rabbits
    0.57
     rumors
    0.56
     acupuncture
    0.56
     Count
    0.55
     damp
    0.54
     intervals
    0.54
    usional
    0.53
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.