© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4-RES-JB
    11. 19661
    Prev
    Next
    INDEX
    Explanations

    references to the company "General Motors" and related entities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of automotive and technology companies, particularly General Motors and General Electric

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

    No Comments

    Negative Logits
    GMT
    -0.86
    usc
    -0.69
    bound
    -0.68
    iable
    -0.66
    obin
    -0.64
    thread
    -0.60
     Kenyan
    -0.59
     aber
    -0.59
    ĥ
    -0.59
    ibilities
    -0.58
    POSITIVE LOGITS
     Corporation
    0.95
     Stores
    0.90
     Corp
    0.89
    bourg
    0.79
     Foundation
    0.75
     Ventures
    0.74
     Industries
    0.72
     Ammunition
    0.72
     divest
    0.72
    merce
    0.72
    Activations Density 0.064%

    No Known Activations