© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 627
    Prev
    Next
    INDEX
    Explanations

    words that indicate a recurring monthly time frame or cost

    oai_token-act-pair · gpt-4-turbo

    references to monetary terms, specifically related to monthly payments or bills

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to monthly expenses or costs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UTF
    -0.90
    lda
    -0.84
    raud
    -0.75
    LESS
    -0.74
    utf
    -0.74
    argon
    -0.72
    yer
    -0.72
    amar
    -0.72
    aine
    -0.71
    ãħĭ
    -0.71
    POSITIVE LOGITS
     installments
    1.07
     upkeep
    1.00
     occas
    0.94
     monthly
    0.89
     subscriptions
    0.87
     intervals
    0.87
     weekly
    0.85
     premiums
    0.83
     roundup
    0.82
     subscription
    0.82
    Activations Density 0.008%

    No Known Activations