INDEX

Explanations

intensifiers and expressions of enthusiasm or emphasis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

Scénario

-0.63

 demikian

-0.62

 Wiseman

-0.61

 Pape

-0.61

اتي

-0.61

NOC

-0.60

crd

-0.60

 kühl

-0.58

それでも

-0.58

formik

-0.57

POSITIVE LOGITS

 REALLY

0.82

 really

0.73

ibatis

0.72

really

0.71

mergeFrom

0.68

benar

0.64

 realy

0.64

 Really

0.63

 quite

0.62

 estate

0.62

Activations Density 0.069%

intensifiers and expressions of enthusiasm or emphasis

No Comments

No Known Activations