© 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. 7-RES-JB
    11. 5358
    Prev
    Next
    INDEX
    Explanations

    words related to incentivization or motivation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to incentives and social stigmatization

    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
    avorite
    -0.71
     blindly
    -0.66
     felon
    -0.64
    tower
    -0.61
     Attorney
    -0.60
     thence
    -0.59
     resemb
    -0.59
    hair
    -0.58
    FAQ
    -0.58
    REE
    -0.58
    POSITIVE LOGITS
    izing
    2.32
    ized
    2.31
    ization
    2.25
    ised
    2.12
    ising
    2.10
    izations
    2.08
    izers
    2.05
    isation
    2.01
    izes
    1.98
    ize
    1.94
    Activations Density 0.092%

    No Known Activations