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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2-RES-JB
    11. 17890
    Prev
    Next
    INDEX
    Explanations

    words related to fundamental concepts or foundational elements

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "basic" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Avoid
    -0.74
    Chance
    -0.69
    Magazine
    -0.66
     Avoid
    -0.63
    å°Ĩ
    -0.63
    âĹ¼
    -0.62
     Mouth
    -0.61
    Discuss
    -0.61
    /-
    -0.61
    Gate
    -0.60
    POSITIVE LOGITS
    basic
    1.09
     necessities
    1.04
     arithmetic
    0.96
     tenets
    0.88
     basic
    0.86
     basics
    0.82
    essential
    0.82
     essentials
    0.82
    Basic
    0.82
     gist
    0.77
    Activations Density 0.012%

    No Known Activations