INDEX

Explanations

references to processes and mechanisms related to knowledge acquisition or development

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

followed by pronouns

np_acts-logits-general · gemini-2.0-flash

know about family

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

IVEREF

-0.64

joje

-0.62

ParallelGroup

-0.61

usermodel

-0.60

οιν

-0.58

 –,

-0.55

rosserie

-0.54

?",

-0.54

AxisAlignment

-0.54

 notwithstanding

-0.53

POSITIVE LOGITS

we

1.34

you

1.10

 EconPapers

0.84

he

0.82

 they

0.72

0.71

we

0.68

私たちは

0.64

دانشنامهٔ

0.64

 você

0.64

Activations Density 0.712%

references to processes and mechanisms related to knowledge acquisition or development

followed by pronouns

know about family

No Comments

No Known Activations