INDEX

Explanations

HTML and formatting tags in text

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

-0.54

-0.51

eclamp

-0.51

XtraEditors

-0.50

UAGES

-0.49

 Torre

-0.48

set

-0.47

enumi

-0.47

ｭ

-0.47

POSITIVE LOGITS

<em>

1.07

<strong>

0.96

 theſe

0.92

 myſelf

0.91

 becauſe

0.90

 iſt

0.86

 reaſon

0.86

 itſelf

0.85

 beſt

0.83

 niedersachsen

0.82

Activations Density 0.127%

HTML and formatting tags in text

No Comments

No Known Activations