© 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. 4103
    Prev
    Next
    INDEX
    Explanations

    mentions of people taking actions or making decisions

    oai_token-act-pair · gpt-3.5-turbo

    indications of ownership or personal involvement in various situations

    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
     Saud
    -0.70
    mentioned
    -0.69
    Synopsis
    -0.68
    ibrary
    -0.63
    "],
    -0.63
    example
    -0.62
    aughs
    -0.61
    daq
    -0.61
    rack
    -0.61
     Seraph
    -0.60
    POSITIVE LOGITS
     intent
    0.96
     intention
    0.87
     intend
    0.85
     intentions
    0.84
     indeed
    0.81
     intends
    0.80
     intended
    0.79
    appro
    0.78
     underestimated
    0.73
     disproportion
    0.73
    Activations Density 0.674%

    No Known Activations