© 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. 9-RES-JB
    11. 7293
    Prev
    Next
    INDEX
    Explanations

    phrases related to destruction and transformation

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to destruction or damage caused by conflict

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Austral
    -0.69
     inexper
    -0.68
     hypocr
    -0.67
    verse
    -0.66
     pedals
    -0.66
     beverages
    -0.65
     inconsistency
    -0.65
     Cec
    -0.65
     necks
    -0.64
     msec
    -0.63
    POSITIVE LOGITS
     redevelopment
    1.05
     redevelop
    1.03
     reopened
    0.97
     renovation
    0.94
     habitable
    0.92
     rubble
    0.91
     lockdown
    0.90
     inhabited
    0.89
     demolition
    0.88
     demolished
    0.88
    Activations Density 0.564%

    No Known Activations