© 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. 7566
    Prev
    Next
    INDEX
    Explanations

    words related to predatory behavior or potential dangers

    oai_token-act-pair · gpt-3.5-turbo

    references to predators and predatory behavior

    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
     provisional
    -0.79
    oard
    -0.75
    bel
    -0.75
    gran
    -0.74
    VK
    -0.72
    rique
    -0.70
    ahon
    -0.69
    UGE
    -0.68
    rief
    -0.68
    printed
    -0.68
    POSITIVE LOGITS
     predators
    1.29
     prey
    1.13
     predator
    1.07
     Predators
    0.85
    ervative
    0.84
     stalking
    0.84
     predatory
    0.80
     instincts
    0.79
    ervatives
    0.78
     carniv
    0.78
    Activations Density 0.018%

    No Known Activations