© 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. 1061
    Prev
    Next
    INDEX
    Explanations

    the word "St. Kitts" or variations related to it

    oai_token-act-pair · gpt-3.5-turbo

    the letter 's'

    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
    asma
    -0.84
    odder
    -0.72
    âĶ
    -0.70
    affer
    -0.69
    ydia
    -0.69
    orr
    -0.68
    aeus
    -0.63
    enhagen
    -0.63
    sers
    -0.63
    istries
    -0.61
    POSITIVE LOGITS
    £ı
    0.83
    âĹ¼
    0.81
    Į
    0.80
    ģĸ
    0.77
     Earthquake
    0.75
    ¶
    0.72
    Ī
    0.72
    naire
    0.70
     Galile
    0.70
     Atomic
    0.69
    Activations Density 0.000%

    No Known Activations