© 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. 9-RES-JB
    11. 5247
    Prev
    Next
    INDEX
    Explanations

    phrases related to pledging or backing a project in a crowdfunding context

    oai_token-act-pair · gpt-3.5-turbo

    terms related to rewards and incentives in a crowdfunding context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quickShipAvailable
    -0.85
    inventoryQuantity
    -0.82
     scandals
    -0.79
     killings
    -0.78
    viol
    -0.71
    polit
    -0.69
    ilic
    -0.69
    violence
    -0.67
     homicides
    -0.66
    phis
    -0.66
    POSITIVE LOGITS
     FREE
    1.02
     discounted
    1.01
     bonus
    0.96
     complimentary
    0.96
     unlimited
    0.93
     refund
    0.93
     refunds
    0.91
     Lifetime
    0.89
     exclusive
    0.88
     PLUS
    0.87
    Activations Density 0.335%

    No Known Activations