INDEX

Explanations

terms related to compression

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

fractal

-0.71

DispatchToProps

-0.65

nloa

-0.64

 Obrador

-0.63

Παραπομπές

-0.62

felf

-0.61

پیوند

-0.61

ozof

-0.61

 aDecoder

-0.60

avits

-0.59

POSITIVE LOGITS

Minnesota

0.94

 Minnesota

0.92

 Compression

0.81

 distracted

0.81

 compression

0.76

 distractions

0.76

 thunder

0.73

 Borel

0.72

Compression

0.72

 ľud

0.71

Activations Density 0.165%

terms related to compression

No Comments

No Known Activations