© 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. 6-RES-JB
    11. 17102
    Prev
    Next
    INDEX
    Explanations

    phrases related to conditions, tasks, or actions that can potentially have consequences or outcomes

    oai_token-act-pair · gpt-3.5-turbo

    pronouns indicating choice and agency

    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
     Forth
    -0.71
    odore
    -0.67
    wikipedia
    -0.62
     Paraly
    -0.62
     Ammunition
    -0.60
     Resurrection
    -0.60
     Journals
    -0.60
     Orbital
    -0.59
    ption
    -0.59
     Eleven
    -0.59
    POSITIVE LOGITS
     were
    0.75
     weren
    0.74
    're
    0.73
    ammed
    0.71
    utm
    0.70
     stray
    0.68
    ierrez
    0.67
     regul
    0.65
    arer
    0.65
     subscribed
    0.65
    Activations Density 0.196%

    No Known Activations