© 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. 7816
    Prev
    Next
    INDEX
    Explanations

    instances where opinions or beliefs are being stated about what the general population or a majority of people would think or do

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases indicating likelihood or expectations

    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
    rylic
    -0.66
    Liter
    -0.60
     Resurrection
    -0.60
     renaissance
    -0.59
     feasibility
    -0.59
     unification
    -0.58
    inventoryQuantity
    -0.58
     Advertisement
    -0.58
    soType
    -0.57
    orius
    -0.57
    POSITIVE LOGITS
     gladly
    1.02
     be
    0.97
     doubtless
    0.97
     inevitably
    0.93
     undoubtedly
    0.91
     surely
    0.89
     understandably
    0.87
     suffice
    0.86
     attest
    0.85
     argue
    0.85
    Activations Density 0.247%

    No Known Activations