INDEX

Explanations

questions beginning with "why" or "how."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

NUMX

-0.58

Поэтому

-0.49

 sécher

-0.44

קישורים

-0.43

{}".

-0.42

oof

-0.42

escrit

-0.41

{}'.

-0.40

elif

-0.40

aarrggbb

-0.39

POSITIVE LOGITS

How

0.92

Why

0.89

How

0.88

 What

0.84

Why

0.84

What

0.81

Who

0.80

Who

0.76

¿

0.73

Which

0.71

Activations Density 0.227%

questions beginning with "why" or "how."

No Comments

No Known Activations