© 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. 1-RES-JB
    11. 20839
    Prev
    Next
    INDEX
    Explanations

    instances of the word "customer"

    oai_token-act-pair · gpt-3.5-turbo

    references to customers and their experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Alz
    -0.79
    laus
    -0.76
    apo
    -0.71
    abil
    -0.69
    FLAG
    -0.68
     Nobel
    -0.66
     Pill
    -0.66
     Sul
    -0.65
     Chance
    -0.65
     Instruments
    -0.64
    POSITIVE LOGITS
    ele
    1.02
     customer
    0.96
     customers
    0.94
    Customer
    0.88
    atical
    0.82
     deliveries
    0.80
    awei
    0.78
     satisf
    0.77
     cust
    0.76
     Customer
    0.76
    Activations Density 0.008%

    No Known Activations