INDEX

Explanations

code-related comments and directives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 raiſ

-1.05

 Anſ

-0.98

 ſaid

-0.98

 ſtand

-0.97

 Roskov

-0.95

 ſhould

-0.93

SourceChecksum

-0.93

 pleaſure

-0.92

 uſed

-0.92

 ſta

-0.92

POSITIVE LOGITS

region

1.14

 region

0.86

Region

0.81

 Region

0.80

 defaultstate

0.70

regions

0.63

endregion

0.61

 REGION

0.61

 regions

0.59

REGION

0.57

Activations Density 0.144%

code-related comments and directives

No Comments

No Known Activations

code-related comments and directives

No Comments

No Known Activations