© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 7939
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    patch
    -0.73
    LEY
    -0.70
    heads
    -0.70
     crore
    -0.64
    jee
    -0.64
    ces
    -0.62
     Aval
    -0.60
    brow
    -0.60
     PubMed
    -0.59
    de
    -0.59
    POSITIVE LOGITS
    emis
    0.93
    yss
    0.92
    inx
    0.83
     tiss
    0.82
    engeance
    0.80
    inen
    0.79
    odder
    0.77
    imeters
    0.76
    odox
    0.76
    etheus
    0.75
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.