© 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. 0-RES-JB
    11. 22286
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Sant" occurring in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Sant" and related variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iframe
    -0.74
    ################
    -0.70
     binding
    -0.70
     cursor
    -0.68
     craw
    -0.68
     arrow
    -0.66
     eq
    -0.66
     Blink
    -0.66
    mouse
    -0.65
     integer
    -0.65
    POSITIVE LOGITS
     Sant
    3.88
     Santos
    1.36
     Santana
    1.30
     Sag
    1.24
     Agu
    1.21
     Santa
    1.21
     Sard
    1.19
    Santa
    1.19
     Cort
    1.10
     Mant
    1.09
    Activations Density 0.024%

    No Known Activations