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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 21152
    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
    ×ij
    -0.74
    Code
    -0.71
    PART
    -0.69
    ä¸Ń
    -0.67
    PAC
    -0.66
    âĸĦ
    -0.64
    ç
    -0.63
    letters
    -0.62
    íķ
    -0.62
    ãģĤ
    -0.62
    POSITIVE LOGITS
    zynski
    0.80
    ratulations
    0.70
    eway
    0.66
    ettings
    0.66
    iership
    0.65
    inea
    0.65
    uties
    0.64
    ixt
    0.64
    etr
    0.64
    hooting
    0.64
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.