INDEX

Explanations

phrases indicating outcomes or results

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

"Resulted in" or "resulting in"

np_acts-logits-general · gemini-2.0-flash

results in

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

 Administrativna

-0.84

الحياه

-0.73

Viitteet

-0.70

gatsby

-0.68

 Walkover

-0.66

oa̍t

-0.65

Pautan

-0.64

DebuggerNonUser

-0.64

 समीक्षाओं

-0.62

antMatchers

-0.61

POSITIVE LOGITS

 increased

0.71

 eventual

0.66

 powst

0.64

 considerable

0.63

 terjadinya

0.59

 some

0.58

govina

0.58

Corollary

0.57

 eventually

0.57

Activations Density 0.445%

phrases indicating outcomes or results

"Resulted in" or "resulting in"

results in

No Comments

No Known Activations