© 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. 23133
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific person named "Sahni."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Sahni" 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
     Cork
    -0.68
     Beat
    -0.67
     Grounds
    -0.66
     Sparkle
    -0.65
     Liberty
    -0.64
     CLS
    -0.64
     recycle
    -0.60
    Beat
    -0.60
     liberating
    -0.59
     START
    -0.59
    POSITIVE LOGITS
    ni
    3.71
    gi
    2.75
    nia
    1.79
    na
    1.67
    nian
    1.52
    nis
    1.45
    nik
    1.36
    nu
    1.35
    si
    1.25
    nih
    1.25
    Activations Density 0.013%

    No Known Activations