© 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
    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. 23271
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a specific person named "Tr" with varying activations suggesting different contexts or individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to "Tr" or related terms associated with specific organizations or entities

    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
    ELS
    -0.78
    furt
    -0.71
     yeast
    -0.68
    EStream
    -0.67
    MENTS
    -0.67
     arts
    -0.66
     actionGroup
    -0.66
    66666666
    -0.66
    WARE
    -0.65
    eers
    -0.64
    POSITIVE LOGITS
    itton
    1.07
    istan
    1.06
    ilateral
    1.04
    izoph
    1.04
    unn
    1.03
    icol
    1.03
    acer
    1.03
    unks
    0.97
    agic
    0.95
    asury
    0.94
    Activations Density 0.007%

    No Known Activations