© 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. 11434
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically focusing on names of individuals, particularly politicians

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "sen" or related political figures in the text

    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
     bubble
    -0.65
     value
    -0.62
     Floyd
    -0.62
     Pony
    -0.62
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.62
     remedy
    -0.61
     loot
    -0.60
     heal
    -0.60
     devastated
    -0.59
     restoration
    -0.59
    POSITIVE LOGITS
    sen
    4.88
    son
    1.77
    Sen
    1.32
    san
    1.27
    sis
    1.21
    ten
    1.18
    sch
    1.16
    sson
    1.16
    sin
    1.11
    shi
    1.09
    Activations Density 0.010%

    No Known Activations