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. 9691
    Prev
    Next
    INDEX
    Explanations

    formal commands or instructions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to actions and processes, particularly in the context of achieving tasks or goals

    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
    jon
    -0.64
    irez
    -0.55
    abetes
    -0.54
    VIDEO
    -0.52
    lando
    -0.50
    lahoma
    -0.50
    ãģ®ç
    -0.50
    dale
    -0.49
     +++
    -0.49
    omy
    -0.48
    POSITIVE LOGITS
     this
    1.88
     these
    1.64
    this
    1.55
    these
    1.46
     such
    1.36
     THIS
    1.35
     THESE
    1.08
    This
    1.07
    such
    1.03
     This
    1.02
    Activations Density 1.960%

    No Known Activations