INDEX

Explanations

references to numerical data or quantities

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

↵↵

-0.41

-0.40

do

-0.40

-0.36

 по

-0.36

-0.35

int

-0.34

POSITIVE LOGITS

 leaſt

1.23

 propOrder

1.22

 CreateTagHelper

1.06

jmniej

1.01

 Theſe

1.00

 fewest

0.98

awtextra

0.98

Geplaatst

0.97

выше

0.97

 dozen

0.96

Activations Density 0.240%

references to numerical data or quantities

No Comments

No Known Activations