© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 9710
    Prev
    Next
    INDEX
    Explanations

    complex sentences ending in a question

    oai_token-act-pair · gpt-3.5-turbo

    debates or discussions surrounding truth and evidence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Downloadha
    -0.68
    gage
    -0.61
     Rooms
    -0.60
    quished
    -0.58
    senal
    -0.58
    eches
    -0.57
    Street
    -0.57
    iage
    -0.56
    flower
    -0.56
    æ°
    -0.56
    POSITIVE LOGITS
     cynicism
    0.71
     obfusc
    0.68
     nonetheless
    0.66
     causation
    0.66
     misplaced
    0.65
     nutshell
    0.64
     empir
    0.64
     underscore
    0.63
     economists
    0.62
     unanswered
    0.60
    Activations Density 1.339%

    No Known Activations