© 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. 2-RES-JB
    11. 706
    Prev
    Next
    INDEX
    Explanations

    the word "fortune."

    oai_token-act-pair · gpt-4-turbo

    phrases related to wealth or financial abundance

    oai_token-act-pair · gpt-3.5-turbo

    references to wealth or financial gains

    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
    APD
    -0.82
    orney
    -0.76
    Interstitial
    -0.75
    INTON
    -0.74
    organic
    -0.74
    arling
    -0.71
    itarian
    -0.70
    ivity
    -0.69
    oval
    -0.68
    liam
    -0.67
    POSITIVE LOGITS
     fortune
    1.19
     fortunes
    0.99
     tremend
    0.82
     parachute
    0.78
     Seym
    0.75
     mosqu
    0.74
    archy
    0.74
     fortun
    0.73
     contag
    0.69
     surpr
    0.69
    Activations Density 0.006%

    No Known Activations