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. 12343
    Prev
    Next
    INDEX
    Explanations

    phrases related to defending or defense

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "defend" in various contexts

    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
    NetMessage
    -0.70
     explode
    -0.69
    hall
    -0.68
    Ju
    -0.68
    ucket
    -0.63
    foot
    -0.63
    Hop
    -0.63
    Machine
    -0.62
    mad
    -0.62
    bows
    -0.62
    POSITIVE LOGITS
     against
    0.97
    atively
    0.90
     defending
    0.87
     Against
    0.81
     defends
    0.76
    ively
    0.76
    orate
    0.75
    ably
    0.75
    iveness
    0.74
    ously
    0.72
    Activations Density 0.026%

    No Known Activations