INDEX

Explanations

occurrences of the term "G" and related technical specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 direito

-0.47

MOST

-0.45

ilaian

-0.45

клопе

-0.44

 kjem

-0.43

top

-0.42

ew

-0.42

bình

-0.41

asyarakat

-0.41

 lang

-0.41

POSITIVE LOGITS

DOCTYPE

1.08

arXiv

0.95

ReusableCell

0.91

SpringBoot

0.80

UnusedPrivate

0.80

 AspNetCore

0.77

endregion

0.76

 doGet

0.75

 rgba

0.75

extAlignment

0.75

Activations Density 0.026%

occurrences of the term "G" and related technical specifications

No Comments

No Known Activations