© 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. 10-RES-JB
    11. 2821
    Prev
    Next
    INDEX
    Explanations

    words related to financial gain or profit

    oai_token-act-pair · gpt-3.5-turbo

    terms related to profit and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chairs
    -0.69
     Sturgeon
    -0.67
     Alma
    -0.64
     Aval
    -0.62
     Peace
    -0.62
    thia
    -0.62
    Bug
    -0.61
    ocally
    -0.60
    ãĥ¯ãĥ³
    -0.60
    ãĤ³
    -0.59
    POSITIVE LOGITS
     margins
    1.30
     margin
    1.25
    ably
    1.02
     reinvest
    0.97
     motive
    0.96
     profit
    0.90
     profits
    0.88
    nings
    0.87
     earnings
    0.86
     reap
    0.84
    Activations Density 0.039%

    No Known Activations