© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 4059
    Prev
    Next
    INDEX
    Explanations

    phrases related to product releases or launches

    oai_token-act-pair · gpt-3.5-turbo

    sentences ending with a punctuation mark, particularly periods

    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
     trader
    -0.71
    unts
    -0.68
     duct
    -0.67
     trait
    -0.67
    azaki
    -0.66
     charact
    -0.65
     clasp
    -0.64
    roph
    -0.64
    bage
    -0.63
     hug
    -0.62
    POSITIVE LOGITS
     Called
    1.09
     Previously
    1.08
     Specifically
    1.05
     Among
    1.04
     Yesterday
    1.03
     Included
    1.00
     Unfortunately
    0.98
     Congratulations
    0.98
     Shortly
    0.97
     According
    0.96
    Activations Density 0.404%

    No Known Activations