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. 18933
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate comparison or contrast with the term "neither."

    oai_token-act-pair · gpt-3.5-turbo

    the word "neither" in various contexts

    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
    Bang
    -0.72
    Ec
    -0.71
    ÙĴ
    -0.71
    uctions
    -0.71
    uers
    -0.67
    enos
    -0.66
    Vers
    -0.66
    Que
    -0.66
    soType
    -0.64
    ãĥķ
    -0.63
    POSITIVE LOGITS
    theless
    0.75
    !--
    0.75
     sexes
    0.75
     overtly
    0.72
    llor
    0.69
    ndra
    0.66
    soever
    0.66
     shalt
    0.65
     sides
    0.64
    clud
    0.63
    Activations Density 0.009%

    No Known Activations