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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2652
    Prev
    Next
    INDEX
    Explanations

    mentions or references to a specific brand or store name

    oai_token-act-pair · gpt-3.5-turbo

    the word "Gro" and variations, suggesting a focus on a specific brand or product

    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
     innocence
    -0.70
     Leilan
    -0.69
     CPC
    -0.64
    manship
    -0.62
     Legion
    -0.62
     Sons
    -0.62
    UAL
    -0.60
     descendant
    -0.60
     PDT
    -0.60
    ACA
    -0.60
    POSITIVE LOGITS
    tesque
    1.42
    ovy
    1.34
    cery
    1.33
    veland
    1.14
    ggy
    1.13
    tto
    1.10
    tty
    1.08
    ove
    1.07
    hett
    1.00
    ogle
    1.00
    Activations Density 0.027%

    No Known Activations