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

    Neuronpedia

    Jacobian LensNEW
    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. 6-RES-JB
    11. 19639
    Prev
    Next
    INDEX
    Explanations

    terms related to social events or gatherings

    oai_token-act-pair · gpt-3.5-turbo

    references to "reception" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chn
    -0.69
     mortg
    -0.69
    astern
    -0.65
    ucket
    -0.61
    holder
    -0.61
    hed
    -0.60
     diabetic
    -0.60
    Export
    -0.60
    hem
    -0.59
    hov
    -0.56
    POSITIVE LOGITS
    ally
    0.97
    aries
    0.91
    ysis
    0.88
    alled
    0.87
     reception
    0.85
    icable
    0.82
    acion
    0.81
    ennes
    0.79
    ivating
    0.76
    issance
    0.76
    Activations Density 0.033%

    No Known Activations