© 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. 11-RES-JB
    11. 22689
    Prev
    Next
    INDEX
    Explanations

    mentions of past events or historical contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to nostalgic or past experiences

    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
    IDA
    -0.79
    2018
    -0.76
    wake
    -0.75
    oday
    -0.69
     2018
    -0.68
    2015
    -0.68
    2017
    -0.67
    >>>
    -0.67
     Retrieved
    -0.66
     expire
    -0.65
    POSITIVE LOGITS
     unthinkable
    0.85
     unimaginable
    0.75
     typew
    0.72
     taboo
    0.65
     RPGs
    0.65
     feared
    0.65
     computers
    0.64
     primitive
    0.64
     invincible
    0.63
     fashionable
    0.63
    Activations Density 0.413%

    No Known Activations