© 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. 11-RES-JB
    11. 24454
    Prev
    Next
    INDEX
    Explanations

    instances where someone or something is being criticized for going too far in an action or decision

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "in"

    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
    wine
    -0.77
    imental
    -0.72
    OGR
    -0.71
    sonian
    -0.69
    soever
    -0.67
    ALSE
    -0.66
    estyles
    -0.65
     Played
    -0.65
    IAL
    -0.64
    iste
    -0.64
    POSITIVE LOGITS
     locating
    1.31
     recommending
    1.31
     selecting
    1.30
     achieving
    1.28
     enforcing
    1.28
     obtaining
    1.28
     pursuing
    1.28
     determining
    1.28
     asserting
    1.27
     administering
    1.26
    Activations Density 0.168%

    No Known Activations