© 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. 7-RES-JB
    11. 20881
    Prev
    Next
    INDEX
    Explanations

    terms related to public reactions or responses

    oai_token-act-pair · gpt-3.5-turbo

    discussions about public reactions and opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tein
    -0.85
     bis
    -0.66
     possessions
    -0.66
     ×
    -0.62
     navig
    -0.61
     Constitution
    -0.61
     Ops
    -0.59
     coordinates
    -0.59
     geometry
    -0.58
     feat
    -0.57
    POSITIVE LOGITS
    isSpecialOrderable
    0.94
     reaction
    0.93
     disapproval
    0.90
     outcry
    0.88
     backlash
    0.88
    DragonMagazine
    0.88
     reactions
    0.85
    soType
    0.83
     condemnation
    0.82
     clam
    0.79
    Activations Density 0.343%

    No Known Activations