© 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. 4348
    Prev
    Next
    INDEX
    Explanations

    words related to masquerading or concealment

    oai_token-act-pair · gpt-3.5-turbo

    references to culinary measurements or recipes involving mashed items

    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
    BOOK
    -0.82
    ACTED
    -0.72
    OWN
    -0.67
    BY
    -0.66
    ORD
    -0.66
    LESS
    -0.65
    ï¸ı
    -0.64
     Coffin
    -0.63
     Corinthians
    -0.63
     Geneva
    -0.62
    POSITIVE LOGITS
    querade
    1.39
    quer
    1.25
     mas
    0.97
    ques
    0.90
    que
    0.90
    isy
    0.86
    iscal
    0.85
    asonic
    0.82
    oles
    0.79
    aques
    0.79
    Activations Density 0.003%

    No Known Activations