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

    Neuronpedia

    Jacobian LensNEW
    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. 9-RES-JB
    11. 6043
    Prev
    Next
    INDEX
    Explanations

    phrases related to negative consequences or threats

    oai_token-act-pair · gpt-3.5-turbo

    content related to business-related challenges and losses

    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
     Cosponsors
    -0.70
     Latest
    -0.67
     Canaver
    -0.66
    mega
    -0.59
     TBA
    -0.58
     pioneered
    -0.57
    Quant
    -0.55
    soDeliveryDate
    -0.55
     Originally
    -0.55
     Rept
    -0.54
    POSITIVE LOGITS
     valuable
    0.83
     benefit
    0.79
     subsequent
    0.76
     chances
    0.75
     worthwhile
    0.75
     unwanted
    0.73
     profit
    0.73
     undes
    0.73
     credibility
    0.73
     detriment
    0.72
    Activations Density 1.167%

    No Known Activations