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. 11113
    Prev
    Next
    INDEX
    Explanations

    verbs related to making requests or giving instructions

    oai_token-act-pair · gpt-3.5-turbo

    actions that involve requests or instructions

    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
    requires
    -0.79
     Appears
    -0.71
     Prelude
    -0.66
    abiding
    -0.64
    productive
    -0.64
    lines
    -0.64
    tions
    -0.63
    etheless
    -0.63
    pite
    -0.61
    ults
    -0.60
    POSITIVE LOGITS
     participate
    1.07
     remove
    0.97
     reconsider
    0.97
     postpone
    0.94
     partake
    0.92
     give
    0.92
     keep
    0.91
     join
    0.91
     preserve
    0.89
     undertake
    0.89
    Activations Density 0.088%

    No Known Activations