© 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. 10-RES-JB
    11. 10516
    Prev
    Next
    INDEX
    Explanations

    phrases related to violent incidents or accidents

    oai_token-act-pair · gpt-3.5-turbo

    references to violent incidents or emergencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    peak
    -0.70
    ħĭ
    -0.69
     retiring
    -0.67
     recommending
    -0.64
     revise
    -0.63
     persuasion
    -0.63
     forgetting
    -0.63
     Absent
    -0.62
    recomm
    -0.62
    optim
    -0.62
    POSITIVE LOGITS
     occurred
    1.84
     happened
    1.61
     lasted
    1.37
     unfolded
    1.35
     transpired
    1.35
     resulted
    1.28
     coincided
    1.24
     stemmed
    1.23
     occurs
    1.21
     occ
    1.20
    Activations Density 0.240%

    No Known Activations