INDEX

Explanations

instructions related to cooking or food preparation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

ppchen

-0.47

 CORS

-0.47

 crates

-0.47

érêt

-0.47

السلام

-0.46

 crate

-0.45

 Normdatei

-0.45

 TestBed

-0.45

Whitney

-0.44

RegistryLite

-0.44

POSITIVE LOGITS

 dough

1.06

 rolling

0.96

 shaping

0.93

 roll

0.93

 rolled

0.91

 Shaping

0.90

Roll

0.87

 Roll

0.85

roll

0.84

KommentareTeilen

0.84

Activations Density 0.171%

instructions related to cooking or food preparation

No Comments

No Known Activations