© 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. 16895
    Prev
    Next
    INDEX
    Explanations

    mentions of specific professional titles or disciplines

    oai_token-act-pair · gpt-3.5-turbo

    references to specific nationalities or ethnic groups

    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
     snap
    -0.62
     bundle
    -0.61
     stealth
    -0.59
     lasting
    -0.58
    ACTION
    -0.58
     bottom
    -0.58
     Â
    -0.57
     sweet
    -0.57
     storage
    -0.57
     cap
    -0.56
    POSITIVE LOGITS
    ians
    4.52
    ian
    2.90
    IAN
    1.85
    rians
    1.64
    arians
    1.62
    iana
    1.50
    iens
    1.47
    ienne
    1.43
    ias
    1.42
    icians
    1.41
    Activations Density 0.012%

    No Known Activations