© 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. 6-RES-JB
    11. 13453
    Prev
    Next
    INDEX
    Explanations

    positive or neutral terms related to conflict resolution

    oai_token-act-pair · gpt-3.5-turbo

    terms related to resolution and alleviation of problems or conflicts

    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
    ascus
    -0.74
    Ranked
    -0.71
    grave
    -0.66
    idium
    -0.66
     proble
    -0.63
    prem
    -0.63
    awei
    -0.62
     constantly
    -0.62
     cumbers
    -0.62
    orbit
    -0.62
    POSITIVE LOGITS
     enough
    0.83
    thanks
    0.79
     reassure
    0.77
    glers
    0.76
     rapport
    0.75
     thanking
    0.72
    enough
    0.71
     albeit
    0.70
    arming
    0.70
    00200000
    0.69
    Activations Density 1.090%

    No Known Activations