© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11-RES-JB
    11. 1080
    Prev
    Next
    INDEX
    Explanations

    phrases indicating causal relationships

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a cause-and-effect relationship

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ilion
    -0.73
    Ħ¢
    -0.68
    ntil
    -0.67
     Alive
    -0.66
    ntax
    -0.66
    utenberg
    -0.63
    omaly
    -0.62
    perty
    -0.60
     Presence
    -0.60
    rawling
    -0.58
    POSITIVE LOGITS
     leads
    0.92
     prompts
    0.82
     creates
    0.80
     encourages
    0.79
     raises
    0.78
     attracts
    0.78
     contributes
    0.77
     feeds
    0.77
     influences
    0.76
     inspires
    0.76
    Activations Density 0.029%

    No Known Activations