© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 17092
    Prev
    Next
    INDEX
    Explanations

    mentions of criminal activities, particularly murders

    oai_token-act-pair · gpt-3.5-turbo

    references to murder cases and incidents

    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
    •test_feats

    No Comments

    Negative Logits
    wcsstore
    -0.83
    Cola
    -0.78
    BuyableInstoreAndOnline
    -0.69
     reusable
    -0.63
    amaru
    -0.62
    GY
    -0.61
    ãĥķãĤ©
    -0.61
    umar
    -0.59
    licts
    -0.59
    sector
    -0.59
    POSITIVE LOGITS
     spree
    1.18
    ously
    1.02
     mysteries
    0.98
     murder
    0.93
     mystery
    0.92
     rampage
    0.90
     murders
    0.88
    abilia
    0.83
     murderer
    0.81
     victims
    0.80
    Activations Density 0.076%

    No Known Activations