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. 6393
    Prev
    Next
    INDEX
    Explanations

    terms related to the word "Heart"

    oai_token-act-pair · gpt-3.5-turbo

    the word "Heart" and its variations

    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
    aution
    -0.83
    aeda
    -0.81
    BILITIES
    -0.74
     liability
    -0.74
    etheless
    -0.71
    inational
    -0.69
    enance
    -0.68
    BILITY
    -0.65
    ascus
    -0.63
    iries
    -0.63
    POSITIVE LOGITS
    beat
    1.16
    felt
    1.03
    lake
    1.03
    burn
    1.02
    hardt
    0.91
     Hearts
    0.90
    gow
    0.89
    warming
    0.88
    bread
    0.88
    heart
    0.87
    Activations Density 0.018%

    No Known Activations