© 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. 11-RES-JB
    11. 1264
    Prev
    Next
    INDEX
    Explanations

    words related to destruction or negative impact

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to destruction and its consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reviewer
    -0.68
    icians
    -0.65
     McKenna
    -0.64
    yip
    -0.59
    anooga
    -0.58
     OPT
    -0.57
     Supplemental
    -0.57
     Inquis
    -0.56
    antz
    -0.56
    æĦ
    -0.56
    POSITIVE LOGITS
     havoc
    1.12
    cks
    0.98
    uated
    0.87
    gery
    0.76
    orney
    0.75
    aker
    0.73
    oos
    0.73
    olon
    0.72
    uity
    0.71
    eding
    0.70
    Activations Density 0.102%

    No Known Activations