© 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. 17166
    Prev
    Next
    INDEX
    Explanations

    numbers within text related to a specific topic

    oai_token-act-pair · gpt-3.5-turbo

    negative sentiments or negative expressions

    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
    eele
    -0.71
     AVG
    -0.69
     Cassidy
    -0.69
     Starr
    -0.65
     Cecil
    -0.61
     OPEC
    -0.61
     Loll
    -0.59
     Klu
    -0.59
     Witches
    -0.58
     KP
    -0.58
    POSITIVE LOGITS
    mails
    1.35
    mail
    1.34
    commerce
    1.34
    cigarette
    1.22
    expression
    1.08
    ventures
    1.05
    cigarettes
    1.04
    liquid
    1.02
    government
    0.99
    Commerce
    0.99
    Activations Density 0.032%

    No Known Activations