© 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. 16042
    Prev
    Next
    INDEX
    Explanations

    words related to business transactions and discussions

    oai_token-act-pair · gpt-3.5-turbo

    references to accountability in responses

    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
     Whilst
    -0.84
     favourite
    -0.79
     colourful
    -0.70
     BBC
    -0.68
     Adolf
    -0.67
     harbour
    -0.66
     pictured
    -0.66
     Engels
    -0.65
     favoured
    -0.65
     analysed
    -0.64
    POSITIVE LOGITS
    [/
    1.37
    âĢ
    1.23
    ----
    1.06
    .""
    1.03
    ãĢ
    1.03
     âĢ
    1.00
    .''
    0.99
    ,''
    0.98
    -|
    0.96
    âĶ
    0.94
    Activations Density 1.095%

    No Known Activations