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. 12-RES-JB
    6. 15164
    Prev
    Next
    INDEX
    Explanations

    phrases related to hacking activities or incidents

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to hacking activities and the groups involved

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĶĢâĶĢâĶĢâĶĢ
    -0.88
    ã
    -0.81
     seating
    -0.77
    áµ
    -0.76
     aisle
    -0.74
    ãĥĺãĥ©
    -0.73
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.71
    aukee
    -0.70
     pollen
    -0.69
     grandchildren
    -0.68
    POSITIVE LOGITS
     hacker
    2.43
     hackers
    2.33
     hacking
    2.15
     Hacker
    2.07
     hack
    2.01
     Hack
    1.97
     hacked
    1.81
    Hack
    1.79
     hacks
    1.77
    hack
    1.76
    Activations Density 0.409%

    No Known Activations