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. 4537
    Prev
    Next
    INDEX
    Explanations

    Proper nouns related to finance and industry

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the word "Did" and other auxiliary verbs indicative of actions or inquiries

    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
    etheless
    -0.95
    Closure
    -0.76
     flare
    -0.71
    åij
    -0.70
    âĶĢâĶĢ
    -0.68
     totality
    -0.67
    theless
    -0.66
     confinement
    -0.65
     resemb
    -0.64
     reversal
    -0.61
    POSITIVE LOGITS
    ilon
    0.94
    vas
    0.92
    avan
    0.90
    lems
    0.88
    sell
    0.86
    ona
    0.83
    bas
    0.82
    kel
    0.82
    linger
    0.82
    ago
    0.82
    Activations Density 0.073%

    No Known Activations