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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3-RES-JB
    11. 15180
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal and governmental activities

    oai_token-act-pair · gpt-3.5-turbo

    references to formal commands or orders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nerd
    -0.81
     Whitney
    -0.75
     Philly
    -0.74
     Lovecraft
    -0.72
     Geek
    -0.72
     Slate
    -0.70
     Randall
    -0.70
     Whitman
    -0.70
     Roller
    -0.69
    Oregon
    -0.67
    POSITIVE LOGITS
     organis
    0.97
     favourable
    0.96
     authorised
    0.93
     parliamentary
    0.90
     envis
    0.89
     recognised
    0.88
     recognise
    0.88
     organisers
    0.87
     favour
    0.87
     labour
    0.87
    Activations Density 2.695%

    No Known Activations