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. 7-RES-JB
    6. 2426
    Prev
    Next
    INDEX
    Explanations

    keywords related to the physical location or direction within an object

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    issance
    -0.76
    ensable
    -0.72
    ardy
    -0.70
    capital
    -0.69
    ewitness
    -0.69
    istani
    -0.68
    accompan
    -0.68
    iques
    -0.67
    ardi
    -0.67
    rought
    -0.66
    POSITIVE LOGITS
     diameter
    1.08
    most
    0.99
     circumference
    0.95
     thereof
    0.90
     torso
    0.84
     rim
    0.82
     lobe
    0.82
     cyl
    0.82
     shelf
    0.81
     layer
    0.79
    Activations Density 0.107%

    No Known Activations