© 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. 17680
    Prev
    Next
    INDEX
    Explanations

    phrases related to hard work, endurance, and challenging situations

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to struggle, hardship, and social issues

    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
     Saying
    -0.73
    !:
    -0.70
     when
    -0.69
    WHERE
    -0.64
    .:
    -0.61
    cause
    -0.59
     Childhood
    -0.59
     FY
    -0.59
     Added
    -0.58
     Ern
    -0.58
    POSITIVE LOGITS
     dominates
    1.18
     resides
    1.07
     prevailed
    1.06
     predomin
    1.02
     prev
    1.02
     intersect
    0.98
     reign
    0.94
     exceeds
    0.93
     lur
    0.93
     meets
    0.93
    Activations Density 0.383%

    No Known Activations