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. 5-RES-JB
    6. 17817
    Prev
    Next
    INDEX
    Explanations

    phrases related to a small quantity or degree of something

    oai_token-act-pair · gpt-3.5-turbo

    frequently used adverbs and filler words that convey a sense of quality or emphasis

    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
    )].
    -0.72
     Coil
    -0.70
     Warlock
    -0.67
     Divinity
    -0.67
    )=(
    -0.67
     shitty
    -0.65
     vibration
    -0.65
     experimentation
    -0.64
     sacrific
    -0.64
     compliments
    -0.64
    POSITIVE LOGITS
    azeera
    0.89
    ãĥķãĤ©
    0.81
    reet
    0.71
    ihadi
    0.70
    hatt
    0.69
    ãĥ©ãĥ³
    0.69
    abet
    0.69
    abouts
    0.69
    ãĥij
    0.68
    ould
    0.67
    Activations Density 1.155%

    No Known Activations