INDEX

Explanations

the presence of specific scientific terms or notations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

synthesize

-0.64

UnsafeEnabled

-0.64

 otomatig

-0.63

__["

-0.57

 MessageBoxIcon

-0.57

 MotionEvent

-0.56

UserScript

-0.56

 Winn

-0.55

ungkinkan

-0.54

--;

-0.53

POSITIVE LOGITS

mobileqq

0.74

<tr>

0.71

<table>

0.70

</

0.66

omenclature

0.66

cephala

0.64

 Moby

0.63

COUVER

0.61

}/>

0.61

 Benth

0.59

Activations Density 0.087%

the presence of specific scientific terms or notations

No Comments

No Known Activations