© 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. 10-RES-JB
    11. 20259
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal relationships and interactions

    oai_token-act-pair · gpt-3.5-turbo

    instances of trades and exchanges in contexts involving sports or relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Consider
    -0.65
    ithering
    -0.65
    illions
    -0.62
    pport
    -0.61
    polit
    -0.60
     ticking
    -0.59
    udic
    -0.57
     unimagin
    -0.56
    erity
    -0.55
    tty
    -0.55
    POSITIVE LOGITS
     she
    0.91
     he
    0.85
     they
    0.81
     Lopez
    0.79
     Neal
    0.75
     Meow
    0.73
     him
    0.72
     Garcia
    0.72
     Sawyer
    0.72
    she
    0.71
    Activations Density 0.898%

    No Known Activations