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. 21426
    Prev
    Next
    INDEX
    Explanations

    phrases describing bringing something to life or vividly portraying it

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of bringing something to life or revitalizing it

    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
    alid
    -0.79
    ession
    -0.79
    akedown
    -0.79
    Wed
    -0.72
    Vi
    -0.70
    ª
    -0.67
     Guilty
    -0.66
     Cosponsors
    -0.64
    Ey
    -0.63
    ammy
    -0.63
    POSITIVE LOGITS
     anew
    0.88
    boats
    0.77
    blood
    0.74
    forms
    0.74
    aces
    0.71
    lihood
    0.70
     everlasting
    0.69
    boat
    0.69
     sensations
    0.69
    transform
    0.69
    Activations Density 0.033%

    No Known Activations