© 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. 3931
    Prev
    Next
    INDEX
    Explanations

    phrases or entities that have been officially recognized or declared

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "officially"

    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
    ocene
    -0.76
    wich
    -0.75
    ĸļ
    -0.74
     Emin
    -0.73
     Velocity
    -0.70
    vae
    -0.68
    ritch
    -0.68
     Basin
    -0.68
    nesota
    -0.67
    rug
    -0.67
    POSITIVE LOGITS
     officially
    0.94
     sanctioned
    0.85
     declared
    0.81
     formally
    0.81
     disbanded
    0.81
     endorsed
    0.79
     cleared
    0.78
     declare
    0.78
    named
    0.78
    wcs
    0.76
    Activations Density 0.008%

    No Known Activations