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. 11031
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Panache" which is related to style and flair

    oai_token-act-pair · gpt-3.5-turbo

    references to the topic of "Panchakarma" or related Ayurvedic treatments

    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
     flu
    -0.69
     Vu
    -0.68
     fluids
    -0.67
     Flu
    -0.66
     Relic
    -0.66
     sodium
    -0.65
     numbered
    -0.65
     registration
    -0.65
     printed
    -0.64
     Pro
    -0.64
    POSITIVE LOGITS
    anch
    4.51
    anches
    2.13
    anche
    1.65
    anc
    1.43
     Anch
    1.38
     anchor
    1.23
     anch
    1.18
    ench
    1.13
    anca
    1.07
    anco
    1.06
    Activations Density 0.007%

    No Known Activations