INDEX

Explanations

code snippets or structure that includes specific programming constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

-------

-0.73

rensa

-0.67

 ویکی‌پدیای

-0.67

 Bioaccumulative

-0.65

aronder

-0.64

кобрита

-0.63

JNIEnv

-0.62

 дописавши

-0.61

 touristique

-0.61

duled

-0.59

POSITIVE LOGITS

<unused60>

0.50

 curto

0.49

0.48

0.47

<unused62>

0.46

import

0.46

<unused61>

0.46

Activations Density 0.147%

code snippets or structure that includes specific programming constructs

No Comments

No Known Activations