INDEX

Explanations

numeric values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

✨:

-0.95

 pleaſure

-0.86

IContainer

-0.84

 perſon

-0.83

tagHelperRunner

-0.82

CNP

-0.81

 fubject

-0.80

MOQ

-0.78

 prodi

-0.78

 Jungfrau

-0.78

POSITIVE LOGITS

 years

0.61

 vuotta

0.57

 year

0.56

 besky

0.56

0.55

 изви

0.55

izoen

0.55

 année

0.53

hmac

0.53

jahr

0.52

Activations Density 0.191%

numeric values

No Comments

No Known Activations