INDEX

Explanations

numeric values and percentages in various contexts

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

enumi

-0.49

RenderAtEndOf

-0.48

WireFormatLite

-0.46

{{/

-0.42

rungsseite

-0.42

AutoScaleMode

-0.41

ագրություններ

-0.41

 memin

-0.40

ország

-0.40

ValueStyle

-0.39

POSITIVE LOGITS

 percentage

2.26

 percent

2.14

 percentages

2.11

 Percentage

2.05

percentage

2.01

 PERCENT

2.00

percent

1.99

 Percent

1.98

Percentage

1.98

Percent

1.96

Activations Density 1.779%

numeric values and percentages in various contexts

No Comments

No Known Activations