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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 20166
    Prev
    Next
    INDEX
    Explanations

    words related to emotions and feelings

    oai_token-act-pair · gpt-3.5-turbo

    emotional and psychological states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kills
    -0.58
     Roses
    -0.57
    wolves
    -0.56
    ĪĴ
    -0.55
     GS
    -0.55
    nexus
    -0.55
    archive
    -0.53
    Strike
    -0.53
     Dro
    -0.52
    Chain
    -0.52
    POSITIVE LOGITS
     uncond
    1.00
     insofar
    0.84
     because
    0.83
     irrespective
    0.81
     altogether
    0.80
     regardless
    0.79
     externally
    0.77
     nonetheless
    0.76
     differently
    0.71
     solely
    0.71
    Activations Density 0.526%

    No Known Activations