INDEX

Explanations

references to study results or data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

(\%)

-0.49

 (\%)

-0.49

IActionResult

-0.48

terase

-0.46

+");

-0.46

SuspendLayout

-0.45

$@

-0.42

CppCodeGen

-0.42

\%,

-0.41

arraycopy

-0.41

POSITIVE LOGITS

Personendaten

0.76

][/

0.74

=”

0.73

nofollow

0.67

 GIPHY

0.63

twimg

0.62

=“

0.62

blockquote

0.58

تقاوى

0.57

">“

0.57

Activations Density 2.104%

references to study results or data

No Comments

No Known Activations