Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 20284
    Prev
    Next
    INDEX
    Explanations

    phrases related to political figures and discussions

    oai_token-act-pair · gpt-3.5-turbo

    specific words or phrases related to entertainment or celebrity culture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    !!!!!
    -0.75
     stabilization
    -0.72
     COMPLE
    -0.71
     stabilized
    -0.70
     rebuild
    -0.68
     DATA
    -0.67
     BEFORE
    -0.67
     HUGE
    -0.67
     independ
    -0.67
     Completed
    -0.67
    POSITIVE LOGITS
     greeting
    0.96
     strangers
    0.89
     passers
    0.89
     acquaintances
    0.88
     outsiders
    0.84
     polite
    0.84
     adject
    0.84
     acquaintance
    0.83
    uphem
    0.83
    oqu
    0.82
    Activations Density 0.841%

    No Known Activations