INDEX

Explanations

expressions related to programming syntax or function definitions

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

Lines starting with a plus sign

np_acts-logits-general · gemini-2.0-flash

specific size

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

ItemBackground

-0.75

migrationBuilder

-0.74

rrggbb

-0.72

OrBuilder

-0.72

 ivelany

-0.71

Rhestr

-0.71

Izvori

-0.71

ValueStyle

-0.69

HasForeignKey

-0.67

 ddelweddau

-0.67

POSITIVE LOGITS

0.65

so

0.47

ar

0.46

UTERS

0.45

TEMPO

0.45

Sau

0.43

spieler

0.43

viv

0.43

 Gros

0.43

rawQuery

0.42

Activations Density 0.040%

expressions related to programming syntax or function definitions

Lines starting with a plus sign

specific size

No Comments

No Known Activations