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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 2-RES-JB
    6. 16377
    Prev
    Next
    INDEX
    Explanations

    uncommon or unusual occurrences

    oai_token-act-pair · gpt-3.5-turbo

    terms related to rarity or frequency of occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atta
    -0.85
    uana
    -0.78
    essee
    -0.76
    iang
    -0.72
    reditary
    -0.72
    aling
    -0.72
    rices
    -0.72
    ramid
    -0.72
    elin
    -0.71
    etry
    -0.70
    POSITIVE LOGITS
    ufact
    0.91
    Uncommon
    0.80
    theless
    0.79
    ...]
    0.75
    Īè
    0.74
     Twain
    0.73
    lihood
    0.72
    enance
    0.71
    ceivable
    0.70
     unheard
    0.70
    Activations Density 0.023%

    No Known Activations