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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 10-RES-JB
    6. 1696
    Prev
    Next
    INDEX
    Explanations

    words related to opposing, combating, or countering something

    oai_token-act-pair · gpt-3.5-turbo

    terms related to countering or resisting various challenges or threats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    人
    -0.90
    çĦ
    -0.73
    çīĪ
    -0.69
    iatrics
    -0.68
    ittal
    -0.68
     adorned
    -0.67
    Hig
    -0.66
    ×ķ
    -0.66
    Graph
    -0.65
     Thumbnails
    -0.64
    POSITIVE LOGITS
    balance
    1.07
     criticisms
    0.98
    attack
    0.95
     temptation
    0.95
     criticism
    0.94
     incoming
    0.93
     attacks
    0.92
     unwanted
    0.90
    attacks
    0.89
     attempts
    0.89
    Activations Density 0.128%

    No Known Activations