© 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. 9-RES-JB
    11. 7088
    Prev
    Next
    INDEX
    Explanations

    phrases related to hacking and unauthorized access

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to unauthorized access and hacking activities

    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
    Not in Any Lists

    No Comments

    Negative Logits
    rite
    -0.74
    ãĤ´ãĥ³
    -0.72
    axis
    -0.72
    renheit
    -0.71
    hedon
    -0.71
    rea
    -0.71
    baugh
    -0.70
    olkien
    -0.68
    Percent
    -0.67
    hesis
    -0.66
    POSITIVE LOGITS
     unsuspecting
    1.06
     unwitting
    0.85
     computers
    0.82
     homes
    0.80
     passwords
    0.79
     innocent
    0.79
     minds
    0.78
     wallets
    0.77
     havoc
    0.76
     passports
    0.76
    Activations Density 0.441%

    No Known Activations