Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 10301
    Prev
    Next
    INDEX
    Explanations

    mentions of events, products, or entities being part of a lineup

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "lineup"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nai
    -0.90
    birth
    -0.84
    ricular
    -0.81
    hig
    -0.80
    ryn
    -0.74
    imb
    -0.74
    mit
    -0.73
    bara
    -0.72
    versely
    -0.70
    ode
    -0.69
    POSITIVE LOGITS
     lineup
    1.20
     XI
    0.80
     choices
    0.72
     swaps
    0.72
     selections
    0.72
    DAQ
    0.69
     darling
    0.69
     assignments
    0.67
     XV
    0.66
    naires
    0.66
    Activations Density 0.010%

    No Known Activations