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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 23455
    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
    .""
    -0.74
     territ
    -0.64
     imaginable
    -0.62
     compan
    -0.58
     outwe
    -0.56
    ħĭ
    -0.55
    aminer
    -0.54
     intraven
    -0.54
     medically
    -0.53
     unknow
    -0.53
    POSITIVE LOGITS
    ↵
    1.62
    <|endoftext|>
    0.98
    ↵↵
    0.97
    "},"
    0.81
     By
    0.77
    ↵Âł
    0.76
     Published
    0.69
     However
    0.69
     Originally
    0.68
     Said
    0.68
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.