© 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. 7021
    Prev
    Next
    INDEX
    Explanations

    events or incidents followed by a consequence or action

    oai_token-act-pair · gpt-3.5-turbo

    continuous phrases indicating a sequence of events or actions

    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
    ogly
    -0.76
    rack
    -0.75
    é¾įåĸļ士
    -0.73
    agin
    -0.72
    assed
    -0.72
    ops
    -0.72
    ipers
    -0.70
    ibo
    -0.70
    anuts
    -0.69
    rossover
    -0.67
    POSITIVE LOGITS
     however
    1.12
     rumors
    0.84
     meanwhile
    0.83
     tensions
    0.78
     rumours
    0.73
     analysts
    0.71
     which
    0.70
     hostilities
    0.70
     policymakers
    0.70
     Concern
    0.68
    Activations Density 0.320%

    No Known Activations