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. 1865
    Prev
    Next
    INDEX
    Explanations

    words related to sending or moving something back

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "back" and its various contexts and usages within the text

    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
    inational
    -0.72
    ision
    -0.72
    enaries
    -0.69
    ities
    -0.65
    izo
    -0.64
    entric
    -0.63
    ifix
    -0.62
     viz
    -0.60
    eria
    -0.60
    urable
    -0.60
    POSITIVE LOGITS
    dated
    1.14
    GROUND
    1.09
    packs
    1.01
    wards
    1.00
    fired
    0.96
    )=(
    0.95
    packing
    0.95
    fires
    0.95
    haul
    0.94
    stab
    0.93
    Activations Density 0.059%

    No Known Activations