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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 12-RES-JB
    6. 14543
    Prev
    Next
    INDEX
    Explanations

    adjectives related to strength and power

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

    instances of the word "strong" and its variations related to significance or intensity

    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
     unfocusedRange
    -0.75
     Sloan
    -0.68
    oleon
    -0.67
     postp
    -0.63
     minimized
    -0.63
     Newly
    -0.62
     pandemonium
    -0.62
    cus
    -0.62
     Vanity
    -0.61
    racuse
    -0.60
    POSITIVE LOGITS
    arming
    0.95
    man
    0.89
    nesses
    0.88
    arm
    0.87
    ARM
    0.85
     believer
    0.82
    arms
    0.81
     contender
    0.80
    enough
    0.79
     proponent
    0.79
    Activations Density 0.168%

    No Known Activations