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. 2-RES-JB
    6. 8669
    Prev
    Next
    INDEX
    Explanations

    words related to physical health conditions, particularly those related to muscles and nerves

    oai_token-act-pair · gpt-3.5-turbo

    medical and scientific terminology, particularly related to physical health conditions and substances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    appro
    -0.67
     judgment
    -0.66
    aston
    -0.63
     Germany
    -0.62
    ourced
    -0.62
     judgement
    -0.61
    NSA
    -0.60
     Pathfinder
    -0.60
     keeper
    -0.60
    Labour
    -0.59
    POSITIVE LOGITS
    phy
    1.29
    asus
    1.08
    xit
    0.99
    xia
    0.98
    ptoms
    0.94
    onies
    0.93
    lly
    0.93
    lla
    0.92
    ertodd
    0.91
    nces
    0.90
    Activations Density 0.005%

    No Known Activations