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. 21484
    Prev
    Next
    INDEX
    Explanations

    phrases with the word "Sing" in them

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Sing" or its variations related to singing

    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
    Downloadha
    -0.76
     VICE
    -0.76
    berus
    -0.71
    ossession
    -0.71
    izons
    -0.71
    OURCE
    -0.69
    utterstock
    -0.65
    Ĭ±
    -0.65
    ````
    -0.64
    etheless
    -0.64
    POSITIVE LOGITS
    leton
    1.29
    ularity
    1.27
    apore
    1.23
    ling
    1.05
    lers
    1.04
    Sing
    1.03
    ular
    1.01
    lest
    0.97
    rab
    0.97
    mers
    0.97
    Activations Density 0.009%

    No Known Activations