© 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 EvalsExportsinterp-engineNEWAPI 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. 0-RES-JB
    11. 8158
    Prev
    Next
    INDEX
    Explanations

    phrases related to conversations and debates

    oai_token-act-pair · gpt-3.5-turbo

    references to discussions on various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ep
    -0.64
    ensity
    -0.64
    obook
    -0.62
    stasy
    -0.61
     robber
    -0.60
    seless
    -0.59
    alty
    -0.59
    rg
    -0.58
    ality
    -0.58
    aunt
    -0.57
    POSITIVE LOGITS
     discussions
    3.52
     conversations
    2.77
     discussion
    2.29
     debates
    2.24
     talks
    2.21
     deliberations
    2.07
     negotiations
    2.03
     consultations
    1.95
     conversation
    1.86
     meetings
    1.79
    Activations Density 0.021%

    No Known Activations