INDEX

Explanations

terms related to decreases or declines in quantities or values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 AssemblyProduct

-0.81

AsUp

-0.70

 ddelweddau

-0.66

примеча

-0.61

 betweenstory

-0.57

AndEndTag

-0.56

ochemistry

-0.56

ThroughAttribute

-0.55

 esternos

-0.55

IonicModule

-0.55

POSITIVE LOGITS

 reduction

1.07

 reductions

1.05

 decrease

0.99

 reduce

0.95

 reducing

0.95

 decreasing

0.94

 Reduction

0.92

 decreases

0.91

 reduced

0.90

reduce

0.90

Activations Density 0.740%

terms related to decreases or declines in quantities or values

No Comments

No Known Activations