© 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. 0-RES-JB
    11. 1188
    Prev
    Next
    INDEX
    Explanations

    Words related to negative behavior or treatment

    oai_token-act-pair · gpt-3.5-turbo

    terms related to cruelty and inhumanity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     TD
    -0.78
    Met
    -0.75
     Cit
    -0.75
     Amar
    -0.74
     MET
    -0.72
    ERT
    -0.70
     Kislyak
    -0.70
    mint
    -0.70
     Jarrett
    -0.69
     MP
    -0.69
    POSITIVE LOGITS
     cruel
    3.12
     cruelty
    3.01
     Cruel
    2.55
    humane
    2.12
     humane
    2.01
     inhuman
    1.76
     barbaric
    1.68
    cru
    1.61
     compassionate
    1.54
     brutality
    1.47
    Activations Density 0.029%

    No Known Activations