INDEX

Explanations

references to arms and arm-related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 ModelExpression

-0.65

 GetEnumerator

-0.61

 spitting

-0.61

Rüyada

-0.59

SharedCtor

-0.57

Enumerated

-0.56

Rè

-0.56

 hapa

-0.55

taxa

-0.55

 jumbo

-0.55

POSITIVE LOGITS

Arm

1.20

 arms

1.15

arm

1.11

Arm

1.11

 Arms

1.10

ARM

1.06

Arms

1.01

 ARMS

1.01

arms

0.92

 braço

0.89

Activations Density 0.097%

references to arms and arm-related concepts

No Comments

No Known Activations