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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 7-RES-JB
    6. 20161
    Prev
    Next
    INDEX
    Explanations

    adjectives or nouns related to qualities like simplicity, sincerity, and urgency

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to simplicity and sincerity

    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
    nesium
    -0.73
    iverse
    -0.71
    oval
    -0.66
    nar
    -0.65
    onal
    -0.61
     Sabha
    -0.61
    DA
    -0.61
    vice
    -0.61
    ãĥİ
    -0.61
    har
    -0.60
    POSITIVE LOGITS
    iness
    1.14
    fulness
    0.98
     perv
    0.89
     inherent
    0.88
    iest
    0.86
    ously
    0.81
     quot
    0.81
    lessness
    0.79
    cean
    0.78
    iqueness
    0.77
    Activations Density 0.193%

    No Known Activations