© 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. 4-RES-JB
    11. 450
    Prev
    Next
    INDEX
    Explanations

    objects typically associated with violence, specifically knives

    oai_token-act-pair · gpt-3.5-turbo

    mentions of knives in various contexts

    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
    mberg
    -0.88
    rian
    -0.80
    tainment
    -0.76
    organ
    -0.75
    rians
    -0.74
    phas
    -0.73
    ADRA
    -0.73
    rium
    -0.72
    oral
    -0.72
    oday
    -0.72
    POSITIVE LOGITS
     knives
    1.19
     knife
    1.11
    knife
    1.10
     blades
    1.04
     scissors
    1.02
     blade
    1.01
     Knife
    0.99
     slicing
    0.94
     wielding
    0.89
     claws
    0.87
    Activations Density 0.018%

    No Known Activations