INDEX

Explanations

elements related to numerical data and comparisons

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 kasarigan

-0.70

发表于

-0.65

Tracce

-0.57

enderror

-0.54

}>

-0.54

RenderAtEndOf

-0.54

nesc

-0.53

stini

-0.48

offsetof

-0.48

trage

-0.48

POSITIVE LOGITS

 both

1.66

both

1.47

Both

1.34

 Both

1.24

 everywhere

1.23

 BOTH

1.21

 entrambi

1.18

 både

1.13

BOTH

1.13

everywhere

1.08

Activations Density 0.631%

elements related to numerical data and comparisons

No Comments

No Known Activations