INDEX

Explanations

geographic directions and locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 nahilalakip

-0.68

RenderAtEndOf

-0.65

 OFDb

-0.63

 transfieras

-0.61

tagHelperRunner

-0.61

AutoScaleMode

-0.59

évaluateur

-0.59

 mergeFrom

-0.58

 invokingState

-0.58

ApplicationTests

-0.57

POSITIVE LOGITS

wards

0.87

ward

0.74

most

0.71

 richting

0.62

webElementXpaths

0.61

方向

0.54

 direction

0.51

bound

0.51

чнее

0.48

 approach

0.48

Activations Density 0.144%

geographic directions and locations

No Comments

No Known Activations