INDEX

Explanations

terms related to the immune system and immunological responses

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

"immune" and immunological responses

np_acts-logits-general · gemini-2.0-flash

immune system

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

rungsseite

-0.97

曖昧さ回避

-0.80

MigrationBuilder

-0.78

 autorytatywna

-0.78

 GeoNames

-0.78

 ModelExpression

-0.74

CloseOperation

-0.73

Géographie

-0.72

 CreateTagHelper

-0.72

 manqué

-0.68

POSITIVE LOGITS

 system

0.71

 System

0.56

system

0.51

 status

0.48

UNE

0.46

UNES

0.45

력

0.43

 SYSTEM

0.43

 defesa

0.43

mn

0.43

Activations Density 0.180%

terms related to the immune system and immunological responses

"immune" and immunological responses

immune system

No Comments

No Known Activations