INDEX

Explanations

terms related to execution processes or operations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

MessageTagHelper

-0.88

TMP

-0.79

NTB

-0.78

WebVitals

-0.77

DAZ

-0.76

évaluateur

-0.75

 Barrie

-0.74

Daf

-0.74

 Spri

-0.73

 Sarm

-0.72

POSITIVE LOGITS

 Execution

1.28

 execution

1.25

 EXEC

1.24

EXEC

1.22

 Execute

1.16

 Executes

1.14

 execute

1.12

 executions

1.09

Execution

1.07

exec

1.07

Activations Density 0.059%

terms related to execution processes or operations

No Comments

No Known Activations