© 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. 23234
    Prev
    Next
    INDEX
    Explanations

    phrases related to resolving or reaching agreement on a situation or decision

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "settle" and its variations, indicating a focus on themes of agreement, resolution, or establishing relationships

    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
    eway
    -1.00
    otic
    -0.79
    emonic
    -0.71
     Canaveral
    -0.68
    ritical
    -0.67
    ery
    -0.64
    urated
    -0.64
    eh
    -0.63
    ERSON
    -0.63
    umbnail
    -0.62
    POSITIVE LOGITS
     disputes
    1.05
     down
    0.86
     grievances
    0.86
     settle
    0.85
     peacefully
    0.82
     into
    0.80
     affairs
    0.79
     debts
    0.77
     dispute
    0.76
     settled
    0.76
    Activations Density 0.046%

    No Known Activations