© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 13364
    Prev
    Next
    INDEX
    Explanations

    phrases related to strength and weakness

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to perceptions of weakness and strength

    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
    mentioned
    -0.67
    tions
    -0.65
    iland
    -0.62
    tails
    -0.59
    =#
    -0.59
    ancies
    -0.56
    anooga
    -0.56
    sequently
    -0.55
    undo
    -0.54
    arton
    -0.53
    POSITIVE LOGITS
     underdog
    0.62
     savior
    0.61
     rog
    0.60
     inferior
    0.60
     discipl
    0.60
    chwitz
    0.57
    ".[
    0.57
    pic
    0.56
     coward
    0.56
     utilitarian
    0.56
    Activations Density 0.738%

    No Known Activations