© 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. 4-RES-JB
    11. 7047
    Prev
    Next
    INDEX
    Explanations

    words related to destruction and disruption

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with harmful or disruptive forces

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

    No Comments

    Negative Logits
    ighed
    -0.83
    cedented
    -0.82
    oling
    -0.81
    igon
    -0.77
    olina
    -0.77
    elf
    -0.76
    puter
    -0.76
    ribe
    -0.75
     Veter
    -0.75
    buck
    -0.75
    POSITIVE LOGITS
     impulse
    1.11
     minded
    0.99
     behav
    0.96
     impulses
    0.93
     tendencies
    0.87
     behavi
    0.85
     arts
    0.80
     activity
    0.79
     tools
    0.79
     qualities
    0.78
    Activations Density 0.047%

    No Known Activations