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. 11-RES-JB
    6. 18405
    Prev
    Next
    INDEX
    Explanations

    phrases related to exerting force or pressure on someone or something to do something specific

    oai_token-act-pair · gpt-3.5-turbo

    instances of coercion or force affecting individuals or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    pport
    -0.75
    ording
    -0.67
    izoph
    -0.65
    effect
    -0.59
    ilyn
    -0.59
    padding
    -0.54
     Wish
    -0.54
    demand
    -0.54
    pot
    -0.53
     Conquer
    -0.53
    POSITIVE LOGITS
     into
    1.36
     onto
    1.24
    into
    1.16
     Into
    1.07
     INTO
    1.01
     ashore
    0.94
     away
    0.92
     overboard
    0.87
     out
    0.87
     to
    0.85
    Activations Density 0.216%

    No Known Activations