© 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. 3-RES-JB
    11. 6589
    Prev
    Next
    INDEX
    Explanations

    names and mentions related to the word "inton"

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "Clinton" and its variations in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amaz
    -0.64
     slippery
    -0.63
     brow
    -0.62
    natureconservancy
    -0.62
    compan
    -0.60
     metaph
    -0.59
     hydra
    -0.59
     swollen
    -0.58
     paras
    -0.58
    headed
    -0.58
    POSITIVE LOGITS
    inton
    1.16
    email
    0.99
    ners
    0.94
    eers
    0.83
    ieri
    0.79
    stown
    0.78
    ventions
    0.76
    eering
    0.76
    nel
    0.76
    folios
    0.75
    Activations Density 0.008%

    No Known Activations