© 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. 2-RES-JB
    11. 9054
    Prev
    Next
    INDEX
    Explanations

    verbs related to taking or implementing actions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "adopt" in various forms, indicating acceptance or implementation of policies or measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    selves
    -0.76
    isal
    -0.71
    iday
    -0.66
     Antar
    -0.65
    TPS
    -0.64
    othal
    -0.62
    OIL
    -0.61
    hole
    -0.61
    ibur
    -0.59
    holes
    -0.58
    POSITIVE LOGITS
     adopted
    1.07
     adopt
    1.04
     adopting
    0.88
     adoption
    0.88
    opted
    0.84
    ortion
    0.76
     adop
    0.76
    rities
    0.74
    rador
    0.72
    ivating
    0.71
    Activations Density 0.009%

    No Known Activations