INDEX

Explanations

code structures and functions related to data processing and manipulation

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

Haupt

-0.54

 ujednoznacz

-0.49

 Kurtz

-0.48

اظ

-0.48

 незавершена

-0.47

 gång

-0.46

meros

-0.44

ParallelGroup

-0.43

toHave

-0.43

 xoay

-0.43

POSITIVE LOGITS

 lowest

1.33

 minimum

1.24

 lower

1.23

min

1.17

 Lowest

1.11

 Minimum

1.10

low

1.09

 getMin

1.07

minimum

1.06

lower

1.06

Activations Density 0.547%

code structures and functions related to data processing and manipulation

No Comments

No Known Activations