© 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. 4568
    Prev
    Next
    INDEX
    Explanations

    phrases related to waves or influxes of different phenomena

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to overwhelming quantities or events

    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
    æ³
    -0.71
    iary
    -0.71
    minus
    -0.70
    most
    -0.69
    tein
    -0.69
    acus
    -0.69
    ħĭ
    -0.68
     Solitaire
    -0.68
    jad
    -0.68
    ree
    -0.68
    POSITIVE LOGITS
     negativity
    0.97
     publicity
    0.96
     arrivals
    0.88
     controversy
    0.87
     criticism
    0.85
     incoming
    0.83
     gunfire
    0.83
     attention
    0.81
     misinformation
    0.80
     discontent
    0.79
    Activations Density 0.138%

    No Known Activations