© 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. 6-RES-JB
    11. 10675
    Prev
    Next
    INDEX
    Explanations

    information related to criminal investigations and emergency services

    oai_token-act-pair · gpt-3.5-turbo

    phrases that provide calls to action for reporting information, particularly related to crime or safety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lav
    -0.72
    ãĤ³
    -0.70
     monopol
    -0.67
    outed
    -0.67
    BILL
    -0.66
     populist
    -0.65
     shrew
    -0.65
     monopoly
    -0.63
    Pin
    -0.63
    å¥
    -0.63
    POSITIVE LOGITS
     Investigators
    0.94
     coroner
    0.86
     investigators
    0.81
     investigator
    0.81
     Officers
    0.80
     Lt
    0.80
     Forensic
    0.79
     NTS
    0.78
     troopers
    0.78
     Officer
    0.78
    Activations Density 1.104%

    No Known Activations