© 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. 3272
    Prev
    Next
    INDEX
    Explanations

    phrases related to making plans or agreements

    oai_token-act-pair · gpt-3.5-turbo

    terms related to making plans or organizing actions

    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
    aminer
    -0.77
    SHIP
    -0.76
     stereotype
    -0.63
     dime
    -0.63
    Honest
    -0.62
    Spoiler
    -0.62
     solitary
    -0.62
     Chin
    -0.61
     scratch
    -0.59
     crime
    -0.59
    POSITIVE LOGITS
     arrangements
    1.23
     arrang
    1.09
    ettings
    1.03
    poons
    0.99
    omething
    0.95
     preparations
    0.90
    accompan
    0.86
    etting
    0.86
     procedures
    0.84
     precautions
    0.83
    Activations Density 0.012%

    No Known Activations