INDEX

Explanations

terms related to "central" locations, institutions, or concepts

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

"Central"

np_acts-logits-general · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

jména

-0.49

➟

-0.39

ⓘ

-0.39

 Vernunft

-0.38

calaure

-0.36

seits

-0.36

Ⓘ

-0.35

 türlü

-0.35

StartTag

-0.34

clusal

-0.34

POSITIVE LOGITS

 Central

0.98

Central

0.98

 CENTRAL

0.94

central

0.91

 central

0.88

CENTRAL

0.86

 centrally

0.73

 centrale

0.67

 Zentral

0.66

entral

0.64

Activations Density 0.049%

terms related to "central" locations, institutions, or concepts

"Central"

No Comments

No Known Activations