© 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 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. 10-RES-JB
    11. 4623
    Prev
    Next
    INDEX
    Explanations

    names or terms related to "Con" or "Con" at the start of a word

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Con" followed by numbers or related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disadvantage
    -0.64
     beh
    -0.63
     downside
    -0.63
     Wem
    -0.60
     polarization
    -0.59
     footprints
    -0.58
     downhill
    -0.58
     htt
    -0.58
     flourishing
    -0.58
    assetsadobe
    -0.57
    POSITIVE LOGITS
    venient
    1.35
    crete
    1.35
    ventional
    1.33
    secut
    1.29
    ventions
    1.25
    nell
    1.24
    vict
    1.20
    nery
    1.19
    cerning
    1.18
    roe
    1.16
    Activations Density 0.013%

    No Known Activations