INDEX

Explanations

terms and phrases related to computing, data processing, and technology

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

 iſt

-0.98

 itſelf

-0.98

ſelf

-0.88

.",

-0.80

 raiſ

-0.78

 pleaſure

-0.78

 whoſe

-0.77

 ſind

-0.77

.³

-0.77

 ſta

-0.74

POSITIVE LOGITS

 stuff

0.87

 mierda

0.78

 IIRC

0.74

 REALLY

0.73

 IMHO

0.72

 crappy

0.71

 kinda

0.71

 really

0.69

 crap

0.66

 наверное

0.66

Activations Density 1.909%

terms and phrases related to computing, data processing, and technology

No Comments

No Known Activations