© 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. 1-RES-JB
    11. 8958
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names associated with the act of founding or starting something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "founded."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    othy
    -0.83
    patch
    -0.70
     DOE
    -0.66
     Siberian
    -0.66
    Bron
    -0.65
     Bagg
    -0.65
     Hunter
    -0.64
    isite
    -0.63
    dos
    -0.63
     Peninsula
    -0.61
    POSITIVE LOGITS
     founded
    1.03
    ablished
    0.93
    ãĤ¤ãĥĪ
    0.90
    ãĥ¼ãĥĨãĤ£
    0.87
    ãĥ³ãĤ¸
    0.86
    reprene
    0.86
     Seym
    0.85
    urated
    0.84
    edIn
    0.83
    founded
    0.83
    Activations Density 0.005%

    No Known Activations