© 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. 9-RES-JB
    11. 998
    Prev
    Next
    INDEX
    Explanations

    phrases related to social interactions involving people's behaviors and relationships

    oai_token-act-pair · gpt-3.5-turbo

    themes related to goodwill and community engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ozy
    -0.59
     Boeing
    -0.58
     Arpaio
    -0.58
     Lethal
    -0.57
     Secretary
    -0.57
     prosecut
    -0.56
     lieutenant
    -0.56
     Treasurer
    -0.56
     McDonnell
    -0.56
     Buffett
    -0.55
    POSITIVE LOGITS
    selves
    0.79
     alike
    0.76
     lifestyles
    0.75
     selves
    0.73
     interacting
    0.72
     peacefully
    0.69
     backgrounds
    0.65
     behaviours
    0.64
    their
    0.64
    united
    0.64
    Activations Density 0.926%

    No Known Activations