© 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. 7-RES-JB
    11. 17173
    Prev
    Next
    INDEX
    Explanations

    financial terms and concepts

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to financial expenditures and out-of-pocket costs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    spect
    -0.79
    ierre
    -0.79
    ipolar
    -0.72
    aha
    -0.71
    unci
    -0.70
    ogue
    -0.69
    inson
    -0.68
     Morse
    -0.66
    aptic
    -0.66
    osite
    -0.63
    POSITIVE LOGITS
     expenses
    1.36
     fund
    1.34
     funds
    1.34
     (£
    1.32
     money
    1.30
     payable
    1.29
     payments
    1.29
     ($
    1.26
     reimburse
    1.25
     coffers
    1.23
    Activations Density 0.958%

    No Known Activations