INDEX

Explanations

key terms and phrases associated with influence and significance in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 OFDb

-0.67

IsMutable

-0.58

__(/*!

-0.56

PYX

-0.55

(||

-0.55

 neler

-0.55

onViewCreated

-0.54

eadilan

-0.54

bunya

-0.54

Rè

-0.52

POSITIVE LOGITS

 worth

0.79

 unto

0.78

 used

0.71

 geworden

0.69

par

0.68

 waard

0.68

 deserving

0.65

 worthy

0.65

 bagi

0.64

 schle

0.63

Activations Density 0.618%

key terms and phrases associated with influence and significance in various contexts

No Comments

No Known Activations