INDEX

Explanations

phrases that reference facts, evidence, and summaries of research studies or findings

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

 Мексичка

-0.87

 дописавши

-0.76

KommentareTeilen

-0.70

Personensuche

-0.69

 insuffisamment

-0.69

interopRequire

-0.68

__*/

-0.68

 виправивши

-0.68

ⓧ

-0.67

TestingModule

-0.66

POSITIVE LOGITS

SBATCH

0.51

 Roskov

0.46

WindowConstants

0.43

kregen

0.42

 Calab

0.41

and

0.41

ropathy

0.40

 اليه

0.39

erst

0.38

erba

0.37

Activations Density 0.967%

phrases that reference facts, evidence, and summaries of research studies or findings

No Comments

No Known Activations