INDEX

Explanations

mathematical expressions and terms related to data structures or algorithms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

Ltd

-0.57

She

-0.53

#+#

-0.52

Inc

-0.51

</em>

-0.49

He

-0.48

Bay

-0.48

Jr

-0.47

zug

-0.47

[[

-0.46

POSITIVE LOGITS

IntoConstraints

0.95

 quelcon

0.90

AndEndTag

0.89

 оригіналу

0.77

 preſent

0.77

AnchorStyles

0.76

GEBURTSDATUM

0.74

 ainfi

0.73

RectangleBorder

0.73

 CURLOPT

0.73

Activations Density 1.064%

mathematical expressions and terms related to data structures or algorithms

No Comments

No Known Activations