Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 22441
    Prev
    Next
    INDEX
    Explanations

    sentences that start with "Not only"

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing exclusivity or limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lain
    -0.78
    marine
    -0.73
    pron
    -0.71
    asel
    -0.69
    ller
    -0.66
     Tasman
    -0.65
    "}],"
    -0.64
    yles
    -0.63
    agin
    -0.63
    hyde
    -0.63
    POSITIVE LOGITS
    theless
    0.67
     coincidence
    0.65
    ional
    0.61
    cial
    0.57
    rical
    0.57
     hires
    0.57
     kidding
    0.56
     obe
    0.56
     shalt
    0.55
    onse
    0.55
    Activations Density 0.025%

    No Known Activations