© 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. 8-RES-JB
    11. 1081
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions, decision-making, or observation

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate conclusions or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iste
    -0.65
     sought
    -0.63
     favoured
    -0.63
    orld
    -0.63
     declared
    -0.63
     submitted
    -0.63
     recognised
    -0.63
     conquered
    -0.62
     recognized
    -0.61
     requested
    -0.60
    POSITIVE LOGITS
    ·
    0.84
     Aires
    0.82
    hift
    0.81
     Mahjong
    0.80
     GOODMAN
    0.75
    undown
    0.75
    ITION
    0.72
    ems
    0.69
    Ĥ¬
    0.69
    Myth
    0.67
    Activations Density 0.134%

    No Known Activations