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. 3-RES-JB
    6. 14272
    Prev
    Next
    INDEX
    Explanations

    words related to inherent qualities or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    terms related to inherent qualities or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kers
    -0.99
    uku
    -0.75
    cow
    -0.72
    ker
    -0.71
    chel
    -0.68
    pherd
    -0.68
    ucc
    -0.68
    king
    -0.67
     Sutherland
    -0.66
     Shake
    -0.65
    POSITIVE LOGITS
     inherent
    0.93
     cumbers
    0.92
    ities
    0.77
    urities
    0.77
     flaws
    0.76
     dangers
    0.76
     validity
    0.74
     merits
    0.74
    ãĤ¨ãĥ«
    0.74
     aspects
    0.73
    Activations Density 0.008%

    No Known Activations