INDEX

Explanations

fragments of mathematical expressions and formatting symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

̉

-0.51

 schi

-0.47

ﾟ

-0.43

sov

-0.43

 стан

-0.42

תר

-0.41

 الت

-0.41

Cou

-0.41

tele

-0.41

POSITIVE LOGITS

Efq

1.03

 myſelf

1.00

 pleaſure

0.99

 houſe

0.94

 Jefus

0.94

 Monfieur

0.89

 Majefty

0.86

 ſeveral

0.85

 Theſe

0.85

 raiſ

0.84

Activations Density 0.971%

fragments of mathematical expressions and formatting symbols

No Comments

No Known Activations