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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 68
    Prev
    Next
    INDEX
    Explanations

    terms related to computer security threats, specifically focused on trojans

    oai_token-act-pair · gpt-3.5-turbo

    references to digital security threats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulse
    -0.83
    wives
    -0.80
    ģ«
    -0.76
    IELD
    -0.74
    maxwell
    -0.70
    Ͻ
    -0.69
    elo
    -0.67
    rentices
    -0.64
    wife
    -0.63
    rator
    -0.62
    POSITIVE LOGITS
     tro
    1.20
    tted
    0.97
    dden
    0.84
    tsky
    0.81
    toe
    0.81
    oidal
    0.80
    isure
    0.78
    teenth
    0.75
    tto
    0.71
    bled
    0.70
    Activations Density 0.023%

    No Known Activations