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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 7-RES-JB
    6. 15734
    Prev
    Next
    INDEX
    Explanations

    words related to contests

    oai_token-act-pair · gpt-3.5-turbo

    mentions of contests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    haar
    -0.73
     Leaf
    -0.71
    minent
    -0.70
     Metallic
    -0.69
    ths
    -0.69
    âĹ¼
    -0.68
    ahon
    -0.67
    Torrent
    -0.63
    sterdam
    -0.62
    gap
    -0.61
    POSITIVE LOGITS
    eers
    1.07
    eering
    1.03
    ing
    0.93
    ants
    0.91
    ors
    0.84
    naire
    0.83
    hips
    0.83
    arium
    0.80
    ateurs
    0.78
    eer
    0.77
    Activations Density 0.025%

    No Known Activations