© 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. 3-RES-JB
    11. 9816
    Prev
    Next
    INDEX
    Explanations

    objects related to weapons, specifically knives

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "knife."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mberg
    -0.85
    rian
    -0.84
    rians
    -0.78
    ria
    -0.75
    rix
    -0.75
    isol
    -0.74
    organ
    -0.73
    ourced
    -0.72
    rium
    -0.72
    tainment
    -0.70
    POSITIVE LOGITS
     knives
    1.16
     knife
    1.14
    knife
    1.08
     blade
    1.02
     blades
    0.99
     Knife
    0.95
     scissors
    0.95
     slicing
    0.88
     cutter
    0.84
     claws
    0.84
    Activations Density 0.017%

    No Known Activations