© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 2065
    Prev
    Next
    INDEX
    Explanations

    mentions of opioid-related terms

    oai_token-act-pair · gpt-3.5-turbo

    words with the suffix "iate" or related forms

    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
    fully
    -0.69
    mere
    -0.68
    nature
    -0.66
    marked
    -0.65
    ingen
    -0.65
    tw
    -0.63
    sand
    -0.63
    amy
    -0.61
    lins
    -0.61
     redes
    -0.61
    POSITIVE LOGITS
    iate
    1.26
    iates
    1.08
    iated
    0.95
    iating
    0.94
    iations
    0.87
    iation
    0.86
    uations
    0.82
    rarily
    0.73
    iator
    0.71
    Äĩ
    0.69
    Activations Density 0.023%

    No Known Activations