© 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. 10-RES-JB
    11. 18835
    Prev
    Next
    INDEX
    Explanations

    terms related to biological organisms and their characteristics

    oai_token-act-pair · gpt-3.5-turbo

    references to biological processes and life forms

    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
    Setting
    -0.81
    setting
    -0.72
     Context
    -0.72
    DCS
    -0.70
    esson
    -0.70
    soType
    -0.70
     Horizon
    -0.69
    Asset
    -0.69
     Wrong
    -0.68
    ento
    -0.68
    POSITIVE LOGITS
     thrive
    1.46
     hiber
    1.45
     migrate
    1.37
     inhabit
    1.33
     emit
    1.27
     reproduce
    1.24
     undergo
    1.23
     metabol
    1.22
     survive
    1.21
     thri
    1.19
    Activations Density 0.306%

    No Known Activations