© 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. 0-RES-JB
    11. 8412
    Prev
    Next
    INDEX
    Explanations

    words related to affirmation or confirmation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to being affected by or suffering from a condition or situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Crash
    -0.74
    rose
    -0.73
     Solitaire
    -0.71
    raz
    -0.69
     VC
    -0.68
    VC
    -0.68
    Gi
    -0.65
     =====
    -0.64
    runners
    -0.64
    planned
    -0.64
    POSITIVE LOGITS
     aff
    3.79
     Aff
    1.58
    Aff
    1.45
    aff
    1.22
     afflicted
    1.06
     affirm
    1.06
     cert
    1.05
     affinity
    1.02
     ail
    1.01
     asc
    1.01
    Activations Density 0.012%

    No Known Activations