© 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. 11-RES-JB
    11. 22349
    Prev
    Next
    INDEX
    Explanations

    information related to criminal activities and arrests

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to suspicion and charges of criminal activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Veter
    -0.72
    dt
    -0.69
    awed
    -0.68
    strom
    -0.68
    Winner
    -0.67
    thank
    -0.65
    Reviewed
    -0.63
    fred
    -0.63
     ðŁij
    -0.63
     Dino
    -0.63
    POSITIVE LOGITS
     offences
    1.30
     espionage
    1.29
     treason
    1.21
     smuggling
    1.21
     subversive
    1.21
     terrorism
    1.18
     extremism
    1.14
     organising
    1.13
     separat
    1.13
     organised
    1.13
    Activations Density 0.313%

    No Known Activations