INDEX

Explanations

terms and concepts related to regression analysis and statistical modeling

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

openqa

-0.56

CrossOrigin

-0.54

utkan

-0.52

StructEnd

-0.51

="@+

-0.49

losseum

-0.48

 lizenz

-0.48

 approved

-0.47

 ratified

-0.47

AddRef

-0.46

POSITIVE LOGITS

 observations

0.91

 observation

0.80

 Observations

0.79

 Observation

0.73

 categorical

0.73

 Treatment

0.70

observations

0.70

 covariates

0.69

 OBSERVATIONS

0.69

 treatment

0.67

Activations Density 1.936%

terms and concepts related to regression analysis and statistical modeling

No Comments

No Known Activations