INDEX

Explanations

terms related to scientific analysis and methodology

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

 tartalomajánló

-0.62

ntesis

-0.51

 kasarigan

-0.47

shi

-0.46

xad

-0.46



-0.46

enderror

-0.45

참고

-0.45

стреча

-0.45

hire

-0.44

POSITIVE LOGITS

GraphicsUnit

1.05

@[+][

0.80

 فريبيس

0.79

 linkovi

0.74

andExpect

0.74

ActionCreators

0.72

 مرئيه

0.72

Digitized

0.72

SuccessListener

0.71

ResponseWriter

0.70

Activations Density 0.775%

terms related to scientific analysis and methodology

No Comments

No Known Activations