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. 21673
    Prev
    Next
    INDEX
    Explanations

    words related to medical imaging techniques, especially computed tomography (CT)

    oai_token-act-pair · gpt-3.5-turbo

    words related to different forms of photography and its techniques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    mut
    -0.74
     token
    -0.64
     hig
    -0.63
     jan
    -0.62
     tempered
    -0.60
     fixing
    -0.59
     March
    -0.58
    mas
    -0.58
     equal
    -0.57
     April
    -0.57
    POSITIVE LOGITS
    ography
    4.58
    ographic
    3.16
    ographies
    3.08
    ographers
    3.02
    ographical
    2.95
    ographer
    2.91
    ographically
    2.79
    ographs
    2.27
    ograph
    2.24
    ograp
    2.14
    Activations Density 0.015%

    No Known Activations