© 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
    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. 1288
    Prev
    Next
    INDEX
    Explanations

    phrases that describe or mention different realms, environments, or fields

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate different "worlds" or realms within various contexts

    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
    ptoms
    -0.81
    ilee
    -0.79
     [*]
    -0.75
    amount
    -0.74
    ittees
    -0.70
     omit
    -0.70
    Enlarge
    -0.69
    ittee
    -0.68
    [_
    -0.67
     ende
    -0.66
    POSITIVE LOGITS
     academia
    0.87
     Warcraft
    0.77
     entertainment
    0.75
     Dreams
    0.73
     ours
    0.71
     commerce
    0.70
     tomorrow
    0.69
     hospitality
    0.67
     finance
    0.66
     Grind
    0.65
    Activations Density 0.096%

    No Known Activations