© 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. 11-RES-JB
    11. 10184
    Prev
    Next
    INDEX
    Explanations

    words related to economic well-being and improvement

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the quality or condition of being well or better

    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
     impossibility
    -0.73
    acular
    -0.70
     absurdity
    -0.70
    ãĥīãĥ©ãĤ´ãĥ³
    -0.66
     fallacy
    -0.66
    omore
    -0.65
     inconsistency
    -0.64
    inous
    -0.64
    umo
    -0.63
    ggle
    -0.63
    POSITIVE LOGITS
     equipped
    1.44
     behaved
    1.36
     positioned
    1.34
     compensated
    1.28
     endowed
    1.19
     situated
    1.19
    equipped
    1.18
     educated
    1.16
     disposed
    1.15
    served
    1.15
    Activations Density 0.098%

    No Known Activations