Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 15653
    Prev
    Next
    INDEX
    Explanations

    phrases indicating refusal or reluctance

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "declined."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aptic
    -0.80
    tek
    -0.69
    ulative
    -0.68
    Haunted
    -0.67
    Assembly
    -0.67
    tal
    -0.66
    grain
    -0.66
    ICAN
    -0.66
    Pur
    -0.66
    isf
    -0.65
    POSITIVE LOGITS
     invitations
    0.77
     requests
    0.72
     comment
    0.72
     admission
    0.71
    otiation
    0.71
     Admission
    0.70
     predec
    0.69
    lect
    0.68
     unanimously
    0.68
     respons
    0.68
    Activations Density 0.027%

    No Known Activations