© 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. 3-RES-JB
    11. 15186
    Prev
    Next
    INDEX
    Explanations

    mentions of the keyword "expenditure"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the prefix "Exp" indicating expansions or expenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    warts
    -0.80
    ball
    -0.75
    geist
    -0.71
    wolf
    -0.71
    footed
    -0.70
    ezvous
    -0.67
    balls
    -0.67
    BOOK
    -0.66
    ters
    -0.65
    MET
    -0.64
    POSITIVE LOGITS
    onential
    1.37
    ulsion
    1.34
    anded
    1.21
    onent
    1.20
    ansion
    1.19
    anding
    1.12
    anse
    1.11
    orters
    1.06
    osed
    1.06
    ression
    1.05
    Activations Density 0.005%

    No Known Activations