© 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. 7-RES-JB
    11. 16728
    Prev
    Next
    INDEX
    Explanations

    personal experiences and statements made by individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to identities and social roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     shipment
    -0.66
     waivers
    -0.62
     Voc
    -0.61
     Scher
    -0.60
    ãĥ«
    -0.60
    USS
    -0.60
     Mull
    -0.60
     Intent
    -0.60
     eruption
    -0.59
     Trap
    -0.58
    POSITIVE LOGITS
     myself
    0.98
     ourselves
    0.98
     fortunate
    0.78
     ðŁij
    0.73
     "$:/
    0.70
    £ı
    0.70
     lucky
    0.69
     proud
    0.69
     instinctively
    0.66
     privileged
    0.66
    Activations Density 0.535%

    No Known Activations