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. 6-RES-JB
    6. 22887
    Prev
    Next
    INDEX
    Explanations

    words related to spectroscopy

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "spect" or its variations, indicating a focus on topics related to spectrometry or spectral analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etheless
    -0.80
    side
    -0.62
    mint
    -0.62
    theless
    -0.61
    ¶ħ
    -0.61
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.61
    UNCH
    -0.60
     9000
    -0.58
    capacity
    -0.58
    æ©Ł
    -0.57
    POSITIVE LOGITS
    acular
    1.11
    rums
    1.05
    uous
    1.03
    acles
    1.02
    rils
    0.97
    acle
    0.93
    rosc
    0.91
    ively
    0.91
    ograms
    0.90
    ues
    0.89
    Activations Density 0.021%

    No Known Activations