INDEX

Explanations

references to the achievements and professional roles of individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/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.20.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

PhysRevLett

-0.68

########.

-0.63

ômico

-0.62

Παραπομπές

-0.60

Демографія

-0.59

omiast

-0.59

GEBURTSDATUM

-0.58

CppCodeGen

-0.58

новништво

-0.54

odeon

-0.54

POSITIVE LOGITS

 many

3.02

 numerous

3.00

 several

2.95

several

2.66

Numerous

2.59

many

2.59

 Numerous

2.53

 countless

2.40

 MANY

2.38

Several

2.36

Activations Density 1.918%

references to the achievements and professional roles of individuals

No Comments

No Known Activations