INDEX

Explanations

terms related to representation and demographics in discussions about juries and surveys

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 getItemId

-0.65

gonic

-0.61

ChildScrollView

-0.59

 tetrachloride

-0.59

Rujuakan

-0.59

ainville

-0.58

AutoScaleMode

-0.57

InjectMocks

-0.57

 ddelweddau

-0.57

RestController

-0.56

POSITIVE LOGITS

 demographic

0.76

 demographics

0.74

Demographics

0.71

 Demographic

0.64

 Demographics

0.62

 population

0.62

Demographic

0.59

demographic

0.57

 proportion

0.55

Proportion

0.51

Activations Density 0.856%

terms related to representation and demographics in discussions about juries and surveys

No Comments

No Known Activations