© 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. 9-RES-JB
    11. 9851
    Prev
    Next
    INDEX
    Explanations

    phrases related to criminal cases and legal terms

    oai_token-act-pair · gpt-3.5-turbo

    references to murder and related criminal activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tokens
    -0.81
    TeX
    -0.75
     cancell
    -0.73
     devs
    -0.72
    pmwiki
    -0.71
    taboola
    -0.70
     Unicode
    -0.69
    comments
    -0.69
    Token
    -0.68
    token
    -0.67
    POSITIVE LOGITS
     fatally
    0.98
     unarmed
    0.97
     murder
    0.94
     murdered
    0.94
     gunshot
    0.92
     robbery
    0.91
     burglary
    0.89
     gunned
    0.88
     slaying
    0.87
     stabbed
    0.86
    Activations Density 0.575%

    No Known Activations