INDEX

Explanations

imperative phrases initiating suggestions or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

Efq

-0.84

InjectAttribute

-0.78

 miglia

-0.77

 servici

-0.73

ondissement

-0.70

ulier

-0.68

 numberWith

-0.68

 Hampden

-0.67

 døde

-0.66

 slightest

-0.66

POSITIVE LOGITS

Lets

1.00

 lets

0.96

 Lets

0.89

Давайте

0.73

 tartalomajánló

0.71

Vamos

0.71

TagHelpers

0.68

try

0.68

RenderAtEndOf

0.67

ましょう

0.66

Activations Density 0.101%

imperative phrases initiating suggestions or actions

No Comments

No Known Activations