INDEX

Explanations

the beginning of a text or document

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

Follows "that", "in", or "for"

np_acts-logits-general · gemini-2.0-flash

explaining classifications and definitions

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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



-0.76

ंदीखरीदारी

-0.66

 Normdatei

-0.63

]].

-0.61

".

-0.61

 isoto

-0.60

 bezeichneter

-0.59

®.

-0.57

.";

-0.57

**.

-0.56

POSITIVE LOGITS

is

0.57

 most

0.56

RegistryLite

0.55

__":

0.55

するのは

0.54

的就是

0.54

 Most

0.53

Significant

0.53

 MOST

0.53

したのは

0.52

Activations Density 0.313%

the beginning of a text or document

Follows "that", "in", or "for"

explaining classifications and definitions

No Comments

No Known Activations