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

    Neuronpedia

    Jacobian LensNEW
    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. 3870
    Prev
    Next
    INDEX
    Explanations

    words related to a persistent or ongoing state or action

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "still."

    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
     elimination
    -0.76
    ASE
    -0.72
     Ding
    -0.65
    insula
    -0.64
    ahime
    -0.62
    ANGE
    -0.62
    yrinth
    -0.60
    usterity
    -0.60
    opter
    -0.59
    LEASE
    -0.59
    POSITIVE LOGITS
     exists
    1.03
    birth
    1.03
     retains
    0.97
     owe
    0.91
     owes
    0.91
     resides
    0.90
     haun
    0.89
     manages
    0.88
     existed
    0.87
     maintains
    0.86
    Activations Density 0.070%

    No Known Activations