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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9-RES-JB
    11. 2660
    Prev
    Next
    INDEX
    Explanations

    phrases denoting specific events or situations

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "that" used in various contexts throughout the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nah
    -0.69
     guessing
    -0.68
    istance
    -0.61
    river
    -0.61
    istant
    -0.60
    hare
    -0.58
    Unix
    -0.57
    Being
    -0.57
     Divinity
    -0.57
    omal
    -0.57
    POSITIVE LOGITS
     culminated
    1.37
     lasted
    1.34
     preceded
    1.21
     resulted
    1.18
     spans
    1.12
     culmin
    1.12
     began
    1.11
     ended
    1.10
     ensued
    1.10
     occurred
    1.04
    Activations Density 0.148%

    No Known Activations