INDEX

Explanations

references to "single" and related terms indicating singularity or individual focus

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

following "Single"

np_acts-logits-general · gemini-2.0-flash

single plus descriptive word

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 makl

-0.63

Spoljašnje

-0.59

ValueStyle

-0.56

Notae

-0.54

 localObject

-0.54

 "..\..\

-0.53

__*/

-0.53

 "..\..\..\

-0.51

 cometh

-0.50

grazie

-0.50

POSITIVE LOGITS

ChildScrollView

1.06

handedly

1.04

ReusableCell

0.77

mindedness

0.76

minded

0.76

 malt

0.76

handed

0.73

 minded

0.70

 solitary

0.67

 entity

0.66

Activations Density 0.146%

references to "single" and related terms indicating singularity or individual focus

following "Single"

single plus descriptive word

No Comments

No Known Activations