INDEX

Explanations

negations or expressions of doubt and conditions in statements

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

Preceding "for" (or variants) and related syntax

np_acts-logits-general · gemini-2.0-flash

responsible for

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

expandindo

-1.01

WriteTagHelper

-0.94

 الحره

-0.85

webElementXpaths

-0.85

MigrationBuilder

-0.82

parsedMessage

-0.82

CopyWith

-0.81

Personendaten

-0.75

AntiForgeryToken

-0.74

.*")]

-0.72

POSITIVE LOGITS

for

1.91

for

1.36

 для

1.05

FOR

1.04

For

0.93

 untuk

0.92

 für

0.88

For

0.86

 endfor

0.85

 ervoor

0.83

Activations Density 0.513%

negations or expressions of doubt and conditions in statements

Preceding "for" (or variants) and related syntax

responsible for

No Comments

No Known Activations