© 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. 7-RES-JB
    11. 12634
    Prev
    Next
    INDEX
    Explanations

    mention the word "apostacon" collected from various contexts

    oai_token-act-pair · gpt-3.5-turbo

    substrings commonly associated with the word "apocalypse."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mainline
    -0.64
    trump
    -0.64
     Fargo
    -0.63
    Loop
    -0.60
     Trump
    -0.59
    ãĤ¶
    -0.58
     Slovenia
    -0.57
     Dane
    -0.57
     Swanson
    -0.56
     Loop
    -0.56
    POSITIVE LOGITS
    monary
    0.98
    umatic
    0.80
    aic
    0.79
    irie
    0.79
    imately
    0.78
    incial
    0.76
    earances
    0.76
    rha
    0.76
    ocry
    0.72
    essional
    0.72
    Activations Density 0.146%

    No Known Activations