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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 5-RES-JB
    6. 22013
    Prev
    Next
    INDEX
    Explanations

    phrases related to space missions or astronomy

    oai_token-act-pair · gpt-3.5-turbo

    references to "Plan" indicating a structured approach or project

    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
    wcsstore
    -0.73
     Flavoring
    -0.71
    */(
    -0.71
    NetMessage
    -0.70
    Downloadha
    -0.69
     dab
    -0.66
    ibaba
    -0.65
    soever
    -0.64
    avez
    -0.64
    wrapper
    -0.64
    POSITIVE LOGITS
    etary
    1.04
    escape
    0.99
    ning
    0.97
    ner
    0.92
    isphere
    0.89
    ets
    0.87
    ters
    0.87
     Parenthood
    0.84
    uary
    0.82
    emaker
    0.81
    Activations Density 0.031%

    No Known Activations