INDEX

Explanations

terms related to reduction or minimizing effects

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

the word "reduce" or "reduction"

np_acts-logits-general · gemini-2.0-flash

making less or smaller

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

 doInBackground

-0.88

mobileqq

-0.70

ThroughAttribute

-0.70

]!='

-0.69

 صوتيه

-0.65

frozen

-0.65

 AssemblyProduct

-0.64

askar

-0.62

 föruts

-0.61

mazoo

-0.61

POSITIVE LOGITS

 redu

1.15

 Reduce

1.08

 reduce

1.06

 reduced

1.05

 reduc

1.03

 REDUC

1.03

 Reduced

1.03

 reduction

1.02

Reduce

1.00

 reductions

1.00

Activations Density 0.236%

terms related to reduction or minimizing effects

the word "reduce" or "reduction"

making less or smaller

No Comments

No Known Activations