INDEX

Explanations

technical terminology related to data processing and reconstruction

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

enumi

-0.67

ренко

-0.63

thenes

-0.57

 Viel

-0.56

osti

-0.55

арак

-0.54

 desk

-0.54

://

-0.53

gdx

-0.52

tay

-0.52

POSITIVE LOGITS

 piú

1.09

 feroit

0.96

NUMX

0.94



0.94

 zijne

0.93

 againſt

0.93

 pylint

0.90

出版年

0.90

WebElementEntity

0.90

 zelve

0.90

Activations Density 2.385%

technical terminology related to data processing and reconstruction

No Comments

No Known Activations