INDEX

Explanations

quantifiable attributes or measures in various contexts, such as economic factors or stress-related health indicators

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

MigrationBuilder

-0.70

WebElementEntity

-0.62

RegistryLite

-0.60

 ویکی‌پدی

-0.59

featureID

-0.59

 насељу

-0.58

 समीक्षक

-0.58

 defaultstate

-0.55

modb

-0.52

 članak

-0.52

POSITIVE LOGITS

 defeat

0.90

 defeats

0.84

 fighting

0.82

 defending

0.81

 battle

0.79

 outnumbered

0.79

 strategist

0.78

 strategy

0.78

 opponent

0.77

 tactics

0.77

Activations Density 0.579%

quantifiable attributes or measures in various contexts, such as economic factors or stress-related health indicators

No Comments

No Known Activations