© 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. 13727
    Prev
    Next
    INDEX
    Explanations

    phrases related to different groups or entities being compared or contrasted against each other

    oai_token-act-pair · gpt-3.5-turbo

    entities and groups that impact societal dynamics

    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
    Reply
    -0.74
     Kira
    -0.59
     Pathfinder
    -0.59
     Legacy
    -0.57
     ASA
    -0.57
     Lastly
    -0.57
     CoC
    -0.55
    folio
    -0.55
     Ambrose
    -0.54
     ISO
    -0.54
    POSITIVE LOGITS
     nor
    0.88
     anymore
    0.82
     ones
    0.81
     itself
    0.79
     themselves
    0.73
     guiActiveUn
    0.67
    $.
    0.62
    _.
    0.60
    stasy
    0.59
    osher
    0.59
    Activations Density 0.720%

    No Known Activations