© 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. 6-RES-JB
    11. 23228
    Prev
    Next
    INDEX
    Explanations

    phrases related to engaging in activities or interacting with objects

    oai_token-act-pair · gpt-3.5-turbo

    phrases that involve interacting or engaging with something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fighter
    -0.77
    mart
    -0.70
    anty
    -0.67
    omsky
    -0.66
    FY
    -0.66
    hra
    -0.66
    umbai
    -0.63
    Moh
    -0.63
    sov
    -0.63
    nery
    -0.62
    POSITIVE LOGITS
     dolls
    0.96
     impunity
    0.95
    è¦ļéĨĴ
    0.90
     regards
    0.89
     regard
    0.87
    stood
    0.84
    draw
    0.83
     toys
    0.82
     dignity
    0.77
    standing
    0.77
    Activations Density 0.114%

    No Known Activations