INDEX

Explanations

phrases related to the effectiveness or functionality of 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

@(

-0.55

olyte

-0.52

<>("

-0.52

حياته

-0.52

VON

-0.51

 descon

-0.51

 ansi

-0.51

 Дата

-0.51

Agora

-0.51

ngx

-0.51

POSITIVE LOGITS

 works

0.95

 WORKS

0.90

Works

0.89

works

0.89

 Works

0.88

 miracles

0.85

 fungerar

0.83

 funktioniert

0.83

 funguje

0.82

WORKS

0.81

Activations Density 0.132%

phrases related to the effectiveness or functionality of actions

No Comments

No Known Activations