INDEX

Explanations

instances of the word "for" and variations related to it

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

"For" followed by various words

np_acts-logits-general · gemini-2.0-flash

for specific cases

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

ResumeLayout

-0.57

 sleeves

-0.47

bukkit

-0.42

Attachments

-0.40

تفصیلات

-0.40

 propOrder

-0.40

 eventdata

-0.39

 pips

-0.38

anatomy

-0.37

POSITIVE LOGITS

NameInMap

0.84

 fevere

0.75

bewerken

0.73



0.72

SourceChecksum

0.72

}\}$

0.70

 surla

0.68

ReusableCell

0.68

 Савезне

0.68

 &___

0.68

Activations Density 0.476%

instances of the word "for" and variations related to it

"For" followed by various words

for specific cases

No Comments

No Known Activations