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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8-RES-JB
    11. 628
    Prev
    Next
    INDEX
    Explanations

    phrases related to interaction or involvement between different individuals or groups

    oai_token-act-pair · gpt-3.5-turbo

    actions and activities related to belief, participation, and support among individuals

    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
    asking
    -0.70
    UNCH
    -0.66
    antics
    -0.64
    interstitial
    -0.64
    iven
    -0.62
    hov
    -0.61
    atche
    -0.61
    resso
    -0.61
     Manufacturer
    -0.61
    rison
    -0.61
    POSITIVE LOGITS
    pires
    0.78
     themselves
    0.73
    venant
    0.72
     contrace
    0.70
     misfortune
    0.69
     otherwise
    0.60
     aren
    0.59
     disagrees
    0.58
    eman
    0.58
    ebook
    0.58
    Activations Density 0.293%

    No Known Activations