© 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. 0-RES-JB
    11. 6711
    Prev
    Next
    INDEX
    Explanations

    mentions of the herb 'thyme'

    oai_token-act-pair · gpt-3.5-turbo

    archaic pronouns and references to relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    boxing
    -0.76
     BJ
    -0.73
    Glass
    -0.72
    MAT
    -0.71
    panic
    -0.71
    virtual
    -0.69
    Virtual
    -0.69
     Mesa
    -0.69
     Shooter
    -0.67
     BS
    -0.67
    POSITIVE LOGITS
     thy
    3.37
     Thy
    2.55
     thou
    2.55
     thee
    2.24
     Thou
    2.11
     shalt
    1.65
     ore
    1.34
     faire
    1.23
     thyroid
    1.19
     unto
    1.19
    Activations Density 0.044%

    No Known Activations