© 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. 7-RES-JB
    11. 23513
    Prev
    Next
    INDEX
    Explanations

    phrases related to expressing opinions or giving warnings

    oai_token-act-pair · gpt-3.5-turbo

    statements and warnings regarding social and political issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ecast
    -0.89
    ocument
    -0.82
    ixture
    -0.73
    tyard
    -0.71
    ixt
    -0.68
    adena
    -0.67
    efficients
    -0.64
    ocaust
    -0.64
    andem
    -0.64
    etrical
    -0.62
    POSITIVE LOGITS
     accordingly
    0.96
     afterward
    0.71
     encour
    0.70
     sarcast
    0.70
     stressing
    0.69
     furthermore
    0.68
     vowed
    0.67
     nonetheless
    0.66
     blaming
    0.66
     rhet
    0.64
    Activations Density 0.318%

    No Known Activations