© 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. 6-RES-JB
    11. 13557
    Prev
    Next
    INDEX
    Explanations

    references to a specific source, "Business Insider."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "Business Insider."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sovere
    -0.81
    perm
    -0.78
    liam
    -0.75
    radical
    -0.75
    ensions
    -0.75
    pel
    -0.75
    son
    -0.74
    itional
    -0.74
    fman
    -0.73
    itars
    -0.67
    POSITIVE LOGITS
     Investor
    0.81
    Publisher
    0.74
     Trading
    0.73
     Editorial
    0.72
     Agency
    0.72
     Interview
    0.71
     Nero
    0.71
     Insider
    0.71
     Recomm
    0.70
     Extras
    0.70
    Activations Density 0.023%

    No Known Activations