© 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. 10-RES-JB
    11. 13792
    Prev
    Next
    INDEX
    Explanations

    company or brand names

    oai_token-act-pair · gpt-3.5-turbo

    references to company names and brands

    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
     %%
    -0.70
    interstitial
    -0.69
    xual
    -0.64
     Ort
    -0.64
     Lump
    -0.62
     haun
    -0.61
     tremend
    -0.60
     fallacy
    -0.60
     aka
    -0.60
     retri
    -0.59
    POSITIVE LOGITS
    Corp
    0.89
    tech
    0.84
    Company
    0.83
    Companies
    0.79
    rex
    0.77
     executives
    0.76
     subsidiary
    0.76
    isoft
    0.75
    Mobil
    0.75
     Pharma
    0.74
    Activations Density 0.146%

    No Known Activations