© 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. 22567
    Prev
    Next
    INDEX
    Explanations

    words related to specific individuals, likely a person's name

    oai_token-act-pair · gpt-3.5-turbo

    references to specific names or terms, particularly related to "aurus" and the name "Fowler."

    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
     ip
    -0.70
     damp
    -0.65
     drip
    -0.65
    %"
    -0.62
     colonialism
    -0.62
     ent
    -0.62
    VPN
    -0.60
    text
    -0.60
     bitterly
    -0.59
     Rapp
    -0.59
    POSITIVE LOGITS
    aurus
    5.18
    osaurus
    1.87
    auri
    1.48
    aur
    1.42
    urus
    1.27
    auga
    1.14
    osaurs
    1.08
    qus
    1.08
    etus
    0.98
     Gemini
    0.97
    Activations Density 0.039%

    No Known Activations