Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 12766
    Prev
    Next
    INDEX
    Explanations

    words related to intrusion and breaches in security

    oai_token-act-pair · gpt-3.5-turbo

    terms related to intrusions and security breaches

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

    No Comments

    Negative Logits
    ndra
    -1.06
    å§«
    -0.91
    creen
    -0.91
    wagen
    -0.90
    baum
    -0.86
    BALL
    -0.78
    IELD
    -0.77
    FUL
    -0.72
    cake
    -0.71
    FORE
    -0.69
    POSITIVE LOGITS
    uders
    1.09
     intr
    1.09
    uding
    0.99
    inx
    0.96
    usions
    0.91
    igent
    0.86
    aband
    0.85
    agg
    0.82
    acy
    0.81
    ordinary
    0.80
    Activations Density 0.007%

    No Known Activations