© 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. 22334
    Prev
    Next
    INDEX
    Explanations

    phrases indicating communication or responses from other parties

    oai_token-act-pair · gpt-3.5-turbo

    ongoing communication and feedback related to actions or responses

    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
    mint
    -0.69
     Melt
    -0.63
    weather
    -0.61
    cession
    -0.60
     TAMADRA
    -0.59
     Kills
    -0.57
    inent
    -0.57
     masse
    -0.57
    rament
    -0.57
    resses
    -0.55
    POSITIVE LOGITS
     back
    2.20
    back
    1.95
     backs
    1.83
     BACK
    1.79
     Back
    1.79
    Back
    1.72
    backs
    1.70
    BACK
    1.64
     backward
    1.00
     ago
    0.99
    Activations Density 0.474%

    No Known Activations