© 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. 2804
    Prev
    Next
    INDEX
    Explanations

    words related to generating or producing large amounts of something

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with creating or producing something, especially in financial contexts

    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
    hai
    -0.68
    define
    -0.68
    hid
    -0.68
    >[
    -0.68
    aryn
    -0.68
    ymm
    -0.66
    yer
    -0.66
    untu
    -0.65
    akening
    -0.64
    gerald
    -0.63
    POSITIVE LOGITS
     revenue
    1.08
     revenues
    0.97
     electricity
    0.96
     income
    0.91
     Revenue
    0.86
     excitement
    0.80
     generate
    0.80
     receipts
    0.77
     generates
    0.76
    generated
    0.76
    Activations Density 0.041%

    No Known Activations