© 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. 1-RES-JB
    11. 3125
    Prev
    Next
    INDEX
    Explanations

    the word "digest" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to processing information and food digestion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     illegally
    -0.64
     falsely
    -0.63
    senal
    -0.63
    alien
    -0.63
    proclaimed
    -0.62
    moral
    -0.62
    paralle
    -0.62
    quartered
    -0.61
     tresp
    -0.60
     hire
    -0.59
    POSITIVE LOGITS
     digest
    1.44
    ibility
    1.09
     Digest
    1.05
    ible
    1.02
    ibles
    0.98
    ãĥ¼ãĥĨãĤ£
    0.96
    rition
    0.94
     digestion
    0.90
    ļéĨĴ
    0.88
    rients
    0.85
    Activations Density 0.010%

    No Known Activations