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. 10086
    Prev
    Next
    INDEX
    Explanations

    names related to the surname "Chamcha" or "Cranston"

    oai_token-act-pair · gpt-3.5-turbo

    the name "Cham" and other related names or titles

    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
    uary
    -0.82
     Braun
    -0.71
     HL
    -0.67
    rogen
    -0.66
    âĨ
    -0.65
    lund
    -0.65
     Holmes
    -0.64
    Äĩ
    -0.63
    ð
    -0.61
    uminati
    -0.61
    POSITIVE LOGITS
    plain
    1.13
    perty
    1.05
    essage
    0.98
    plin
    0.92
    pton
    0.89
    borgh
    0.87
    kees
    0.84
     ILCS
    0.83
    ontent
    0.82
    bara
    0.82
    Activations Density 0.016%

    No Known Activations