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. 16743
    Prev
    Next
    INDEX
    Explanations

    the specific name "Sol" with different suffixes and prefixes

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Sol" in various contexts

    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
    shapeshifter
    -0.82
    REE
    -0.67
    è¦ļéĨĴ
    -0.67
    SHIP
    -0.65
    RAFT
    -0.64
    IRD
    -0.64
    alm
    -0.63
    urger
    -0.62
     conscious
    -0.60
     healthy
    -0.60
    POSITIVE LOGITS
    itary
    1.13
    Sol
    1.00
    oshenko
    1.00
    ving
    0.99
    stice
    0.99
    ved
    0.98
    vable
    0.95
    itaire
    0.94
    omon
    0.93
    idon
    0.92
    Activations Density 0.008%

    No Known Activations