© 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. 8-RES-JB
    11. 4561
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial spending and investment

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to spending and financial behavior

    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
    xtap
    -0.84
    ĺħ
    -0.74
    ļ
    -0.65
     Immun
    -0.62
     resurrected
    -0.60
    Ļ½
    -0.60
    Ĭ
    -0.60
    ħĭ
    -0.60
    apest
    -0.59
    ļé
    -0.59
    POSITIVE LOGITS
     than
    1.55
    than
    1.15
     Than
    1.08
     expensive
    0.74
     money
    0.73
    ainers
    0.73
    HUD
    0.72
    ened
    0.72
     bang
    0.71
    ening
    0.69
    Activations Density 0.114%

    No Known Activations