INDEX

Explanations

terms related to neurobiology, particularly involving the entorhinal cortex and its functions

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

The substring "ent"

np_acts-logits-general · gemini-2.0-flash

words starting with ent

np_acts-logits-general · gemini-2.5-flash-lite

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

djangoproject

-0.76

Zeneca

-0.68

 ویکی‌پدی

-0.67

moveToFirst

-0.65

ulario

-0.62

 Waray

-0.59

inverno

-0.59

assium

-0.57

 isComment

-0.56

 répondu

-0.56

POSITIVE LOGITS

ent

0.69

Ent

0.68

ENT

0.62

Ent

0.62

 кӀ

0.58

webElementXpaths

0.58

 المعيارى

0.57

ent

0.56

ENTE

0.54

ENT

0.51

Activations Density 0.140%

terms related to neurobiology, particularly involving the entorhinal cortex and its functions

The substring "ent"

words starting with ent

No Comments

No Known Activations