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. 11884
    Prev
    Next
    INDEX
    Explanations

    phrases related to refusing or rejecting something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "turned down."

    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
    anwhile
    -0.76
    velt
    -0.73
    upper
    -0.72
    insk
    -0.72
    Known
    -0.68
    ollen
    -0.65
     Towns
    -0.65
     Kills
    -0.64
    puted
    -0.64
    atures
    -0.63
    POSITIVE LOGITS
     bribes
    0.72
     fax
    0.67
     requests
    0.66
     extradition
    0.64
     refunds
    0.62
     Kraft
    0.61
     waivers
    0.61
     liking
    0.61
    \">
    0.60
     Blumenthal
    0.60
    Activations Density 0.024%

    No Known Activations