INDEX

Explanations

repeated mentions of "the" and other common phrases to track information density and structure

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

laştır

-0.54

 hombros

-0.52

omas

-0.52

BD

-0.51

!("{

-0.51

 preferencias

-0.50

เย

-0.48

ковы

-0.47

dve

-0.47

 denominator

-0.46

POSITIVE LOGITS

 BoxFit

0.95

ngdoc

0.85

writeFieldEnd

0.85

 Roskov

0.83

AndEndTag

0.82

 bezeichneter

0.82

routeProvider

0.82

 useRouter

0.82

 "..\..\..\

0.80

yscy

0.80

Activations Density 0.102%

repeated mentions of "the" and other common phrases to track information density and structure

No Comments

No Known Activations