INDEX

Explanations

phrases indicating a degree or intensity of something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

zA

-0.55

↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵

-0.55

arco

-0.55

 relâche

-0.55

 Kota

-0.55

zera

-0.54

醐

-0.53

importe

-0.53

RuleContext

-0.52

 ivelany

-0.52

POSITIVE LOGITS

 neighbor

1.18

 neighbors

1.13

 neighbour

1.09

 neighbours

1.03

 Neighbor

0.95

Neighbor

0.92

neighbor

0.90

neighbors

0.88

Neighbour

0.85

 Nachbarn

0.80

Activations Density 0.050%

phrases indicating a degree or intensity of something

No Comments

No Known Activations