INDEX

Explanations

quantitative measures related to size and complexity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

Wider

-0.64

 يتيمه

-0.64

 OMITBAD

-0.57

찮

-0.57

 فريبيس

-0.56

 himo

-0.56

\{\\

-0.54

çası

-0.54

uasion

-0.53

wreck

-0.53

POSITIVE LOGITS

 amount

0.96

 size

0.87

 rate

0.81

amount

0.77

 measured

0.75

 level

0.73

 average

0.72

 value

0.71

 length

0.69

 number

0.69

Activations Density 1.296%

quantitative measures related to size and complexity

No Comments

No Known Activations