© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 8055
    Prev
    Next
    INDEX
    Explanations

    phrases related to venture capital and investment

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "Venture" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ieri
    -0.79
    soDeliveryDate
    -0.70
     subset
    -0.67
     notation
    -0.64
    asting
    -0.64
     sensit
    -0.64
     LW
    -0.63
    OPA
    -0.63
     Gins
    -0.63
    redo
    -0.62
    POSITIVE LOGITS
     Venture
    2.46
     Incredible
    2.03
     Ventures
    1.55
     Banner
    1.27
    ventures
    1.26
    venture
    1.24
     unbelievable
    1.08
     Hulk
    1.07
     Fantastic
    0.98
     Valiant
    0.96
    Activations Density 0.055%

    No Known Activations