Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 16207
    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
    gencies
    -0.74
    idium
    -0.71
    igsaw
    -0.70
    iage
    -0.67
    abil
    -0.67
    âĢİ
    -0.65
    conservancy
    -0.65
     proble
    -0.63
    antz
    -0.63
    ocom
    -0.63
    POSITIVE LOGITS
    ãĥŀ
    0.68
    weet
    0.67
    eport
    0.65
     yuan
    0.59
    hops
    0.58
     Snape
    0.58
    heit
    0.57
    Poké
    0.56
    pring
    0.56
     predictably
    0.55
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.