© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 1892
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences where the word "would" is used to indicate future actions or hypothetical situations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "would" indicating conditional or future actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¦ļéĨĴ
    -0.70
     Relative
    -0.61
     Household
    -0.60
     Sustainable
    -0.60
     Balanced
    -0.59
     Vis
    -0.59
     Cutting
    -0.58
     algorith
    -0.58
     Gutenberg
    -0.57
    building
    -0.57
    POSITIVE LOGITS
     be
    1.10
     gladly
    1.00
     introduce
    0.95
    've
    0.94
     eventually
    0.93
     suffice
    0.93
     doubtless
    0.93
     dearly
    0.89
     arrive
    0.88
    soon
    0.87
    Activations Density 0.167%

    No Known Activations