© 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. 1-RES-JB
    11. 20369
    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
    seys
    -0.82
    ++++++++++++++++
    -0.82
    shaw
    -0.76
    rities
    -0.75
    isations
    -0.75
    mares
    -0.70
    ulates
    -0.68
    mates
    -0.67
    andals
    -0.66
    Dur
    -0.66
    POSITIVE LOGITS
    ĪĴ
    0.79
     cue
    0.70
     disposed
    0.69
     susceptibility
    0.67
     vein
    0.66
     fortun
    0.66
     impulse
    0.66
    ilant
    0.64
    obin
    0.64
     relapse
    0.62
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.