INDEX

Explanations

components related to data processing in experiments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

Eleven

-0.67

Thirty

-0.63

 thirteenth

-0.62

Twelve

-0.62

Fifteen

-0.61

 zwölf

-0.61

eighth

-0.61

 fourteenth

-0.61

 Fourteen

-0.59

 itſelf

-0.59

POSITIVE LOGITS

т

0.84

세

0.75

thr

0.67

 tree

0.65

tri

0.65

 тро

0.62

д

0.61

 thee

0.59

tvo

0.58

τ

0.58

Activations Density 0.372%

components related to data processing in experiments

No Comments

No Known Activations