© 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. 8516
    Prev
    Next
    INDEX
    Explanations

    comments or opinions in a conversational style

    oai_token-act-pair · gpt-3.5-turbo

    statements about team performance and dynamics

    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
    GOP
    -0.95
     Neighbor
    -0.85
     feds
    -0.85
     federally
    -0.83
     Hawai
    -0.82
     HHS
    -0.81
    NPR
    -0.78
     preempt
    -0.78
     GOP
    -0.77
    ASHINGTON
    -0.77
    POSITIVE LOGITS
     analyse
    1.49
     Fifa
    1.25
     analys
    1.16
     tyres
    1.16
     Tottenham
    1.16
     tyre
    1.15
     footballer
    1.14
     realise
    1.14
     organise
    1.14
     Liverpool
    1.13
    Activations Density 0.553%

    No Known Activations