© 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. 13872
    Prev
    Next
    INDEX
    Explanations

    terms related to hacking activities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "hijack" and its variations

    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
    upon
    -0.70
    inez
    -0.70
    ternity
    -0.67
    rose
    -0.66
     condol
    -0.62
    iology
    -0.62
    naire
    -0.61
    inian
    -0.60
    ylon
    -0.60
     Minute
    -0.58
    POSITIVE LOGITS
    acking
    0.85
    aged
    0.84
    querade
    0.82
    eering
    0.81
    ackers
    0.80
    nown
    0.78
     hij
    0.76
    aging
    0.76
    acker
    0.74
    adish
    0.74
    Activations Density 0.051%

    No Known Activations