© 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. 9-RES-JB
    11. 17567
    Prev
    Next
    INDEX
    Explanations

    phrases related to analysis and critique, possibly of written work

    oai_token-act-pair · gpt-3.5-turbo

    elements related to critical reasoning and analysis of arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    unte
    -0.65
    endars
    -0.60
     cabinets
    -0.59
     Volunteers
    -0.59
     magazines
    -0.58
    FACE
    -0.58
     dinners
    -0.57
    ibles
    -0.57
    Crew
    -0.56
    robe
    -0.55
    POSITIVE LOGITS
     empir
    0.90
     causation
    0.84
     nutshell
    0.84
    alogy
    0.81
     intuitive
    0.80
    argument
    0.80
     illustrates
    0.78
     fallacy
    0.78
     succinct
    0.78
     debunk
    0.78
    Activations Density 0.803%

    No Known Activations