© 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. 6-RES-JB
    11. 11605
    Prev
    Next
    INDEX
    Explanations

    phrases indicating high cost or financial resources

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "expensive."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vironment
    -0.87
    mbuds
    -0.86
    mbudsman
    -0.82
     coli
    -0.80
    vous
    -0.78
    soType
    -0.76
    İĭ
    -0.74
    unin
    -0.72
    DEP
    -0.70
    uberty
    -0.69
    POSITIVE LOGITS
     expensive
    1.07
     pric
    0.97
     prohib
    0.91
     pricey
    0.90
    liest
    0.87
     ($
    0.87
     costly
    0.86
     incurred
    0.82
     premiums
    0.81
    ly
    0.81
    Activations Density 0.023%

    No Known Activations