© 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. 16121
    Prev
    Next
    INDEX
    Explanations

    words related to criminal activities or police reports

    oai_token-act-pair · gpt-3.5-turbo

    mentions of authority figures or law enforcement in relation to significant events

    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
    DragonMagazine
    -0.66
    ictional
    -0.58
     %%
    -0.57
    ©¶æ
    -0.56
    iatus
    -0.56
    paralle
    -0.55
    ttle
    -0.55
     parallels
    -0.54
    osate
    -0.54
     Thumbnails
    -0.54
    POSITIVE LOGITS
     said
    1.27
     says
    1.09
    said
    1.03
     told
    1.02
     tells
    1.00
     announced
    0.98
     wrote
    0.95
     Says
    0.92
     explained
    0.92
     reported
    0.91
    Activations Density 0.252%

    No Known Activations