INDEX

Explanations

words related to the concept of being impacted or affected

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 Dumas

-0.88

jsonwebtoken

-0.70

Bissau

-0.69

ertos

-0.68

rumah

-0.68

ymas

-0.66

 Dumont

-0.65

Rha

-0.65

 Manley

-0.63

NewLabel

-0.63

POSITIVE LOGITS

 AFFECT

2.45

 affected

2.45

 affect

2.40

 affects

2.35

affect

2.30

 affecting

2.30

 Affected

2.29

 Affect

2.24

 Affects

2.16

affected

2.12

Activations Density 0.072%

words related to the concept of being impacted or affected

No Comments

No Known Activations