INDEX

Explanations

terms related to employment termination

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Diſ

-0.93

 Anſ

-0.91

 Shakspeare

-0.89

 Monfieur

-0.84

 Reſ

-0.83

 Theſe

-0.80

cipar

-0.79

 inoxid

-0.76

 Conſ

-0.76

 regency

-0.75

POSITIVE LOGITS

 included

0.68

']))

0.67

 recipient

0.64

ass

0.63

 kasarigan

0.60

 components

0.59

 termin

0.57

 terminology

0.57

 inherent

0.57

 component

0.54

Activations Density 0.122%

terms related to employment termination

No Comments

No Known Activations