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. 10840
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a point of emphasis or a notable aspect

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the concept of "not just" to indicate an additional point or clarification

    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
     largeDownload
    -0.84
    oided
    -0.70
    azor
    -0.69
    adish
    -0.69
    ĺħ
    -0.67
    endra
    -0.67
    »Ĵ
    -0.65
    roxy
    -0.64
    stress
    -0.63
    aur
    -0.63
    POSITIVE LOGITS
    ifiable
    1.22
    ifications
    0.91
    itatively
    0.73
     deserts
    0.69
    IFIED
    0.69
    ified
    0.65
    isse
    0.64
     passively
    0.64
     outright
    0.64
    icia
    0.64
    Activations Density 0.035%

    No Known Activations