© 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. 10-RES-JB
    11. 12781
    Prev
    Next
    INDEX
    Explanations

    mentions of personal experiences or anecdotes involving friends and acquaintances

    oai_token-act-pair · gpt-3.5-turbo

    references to personal relationships and friendships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NOW
    -0.77
     understatement
    -0.77
    ardless
    -0.74
     compliant
    -0.70
    excluding
    -0.69
     defenders
    -0.69
    olute
    -0.68
    ctive
    -0.67
    azeera
    -0.67
     Pwr
    -0.66
    POSITIVE LOGITS
     overheard
    1.02
     accidentally
    0.86
     acquaintance
    0.86
     stumbled
    0.83
     Bought
    0.80
     reminis
    0.79
     overhe
    0.78
     wandered
    0.77
     asked
    0.76
     casually
    0.75
    Activations Density 0.536%

    No Known Activations