INDEX

Explanations

references to geographical locations related to natural resource management and wildfires

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 Carbonate

-0.60

enumi

-0.57

 carbonic

-0.56

########.

-0.56

 Skye

-0.56

webElement

-0.54

providedIn

-0.54

+#+#

-0.52

 Kona

-0.51

 Cabo

-0.50

POSITIVE LOGITS

 Fresno

0.73

 Joaquin

0.65

Kern

0.63

NewReader

0.61

illets

0.61

adaptiveStyles

0.61

Fres

0.60

 Modesto

0.60

 Merced

0.59

 Stockton

0.59

Activations Density 0.194%

references to geographical locations related to natural resource management and wildfires

No Comments

No Known Activations