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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 21142
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to planning, strategizing, or preparing for an action

    oai_token-act-pair · gpt-3.5-turbo

    forms of the word "ning" used in various contexts

    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
    ublic
    -0.83
    reon
    -0.79
    rehensive
    -0.77
     Leilan
    -0.76
    Neg
    -0.75
    Altern
    -0.73
    apter
    -0.73
    Weather
    -0.71
    irlf
    -0.70
    ensable
    -0.69
    POSITIVE LOGITS
    ning
    1.12
    ned
    0.90
    HAM
    0.83
    brook
    0.81
    alties
    0.80
    ding
    0.79
    bach
    0.74
    stocks
    0.74
    ham
    0.74
    theless
    0.72
    Activations Density 0.024%

    No Known Activations