© 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. 8-RES-JB
    11. 23395
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing inclusivity or comparison to others

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize inclusivity or universality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     largeDownload
    -0.83
    »Ĵ
    -0.68
    acker
    -0.67
    Ļ½
    -0.66
    ĺħ
    -0.62
    stress
    -0.61
    agus
    -0.60
    ĸļ
    -0.60
    ller
    -0.60
     Genius
    -0.59
    POSITIVE LOGITS
    ifiable
    1.14
    ones
    0.78
    ifications
    0.75
    ional
    0.73
    onto
    0.72
     ones
    0.71
     anymore
    0.70
    here
    0.68
     ours
    0.66
     because
    0.66
    Activations Density 0.027%

    No Known Activations