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. 7-RES-JB
    6. 6781
    Prev
    Next
    INDEX
    Explanations

    phrases related to backing down or retracting statements

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to refusal or persistence in backing down

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anon
    -0.83
    arth
    -0.77
    nesota
    -0.74
    anan
    -0.73
    oven
    -0.70
    lav
    -0.68
    marks
    -0.67
    oran
    -0.67
    teenth
    -0.66
    ross
    -0.65
    POSITIVE LOGITS
     blindly
    0.80
     hesitate
    0.79
     apologise
    0.75
     hesitation
    0.74
     apology
    0.73
     forcefully
    0.73
     uncond
    0.73
     sooner
    0.72
    antic
    0.72
     vigorously
    0.72
    Activations Density 0.159%

    No Known Activations