© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 6898
    Prev
    Next
    INDEX
    Explanations

    terms related to cybersecurity and threat detection

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to cybersecurity threats and measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rontal
    -0.75
    ĸļ
    -0.71
     Anthropology
    -0.69
    acebook
    -0.69
     Vance
    -0.68
     Guinness
    -0.68
    ocally
    -0.67
     NH
    -0.66
     Alive
    -0.66
     Bihar
    -0.65
    POSITIVE LOGITS
     exploiting
    1.07
     aggress
    1.07
     infiltr
    1.03
     harassing
    1.01
     stalking
    1.01
     invading
    1.00
     opportun
    0.99
     exploit
    0.99
     threaten
    0.96
     attacks
    0.95
    Activations Density 1.000%

    No Known Activations