© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 15545
    Prev
    Next
    INDEX
    Explanations

    phrases questioning reasons or causes

    oai_token-act-pair · gpt-3.5-turbo

    questions and phrases emphasizing the concept of "why" or reasons behind actions and situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aughed
    -0.86
    iece
    -0.84
    lator
    -0.80
    ibaba
    -0.79
    iHUD
    -0.70
    yi
    -0.68
    ymph
    -0.68
    utenberg
    -0.67
    arya
    -0.67
    ãĤ´ãĥ³
    -0.64
    POSITIVE LOGITS
    soever
    0.96
     people
    0.85
     they
    0.85
     bother
    0.80
     exactly
    0.79
     someone
    0.79
     somebody
    0.76
     anyone
    0.73
     why
    0.71
     we
    0.70
    Activations Density 0.045%

    No Known Activations