INDEX

Explanations

phrases related to documentation or clarification of missing or included information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/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.17.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

NOPQRST

-0.69

 adipis

-0.61

principalColumn

-0.60

 onCreateView

-0.57

amoan

-0.55

 Kalau

-0.54

>>()

-0.54

elesaikan

-0.54

 AssemblyCompany

-0.54

ondissement

-0.52

POSITIVE LOGITS

的是

0.78

are

0.72

 there

0.59

 were

0.57

的就是

0.55

 adalah

0.51

คือ

0.49

 são

0.49

 насељу

0.48

Included

0.48

Activations Density 0.190%

phrases related to documentation or clarification of missing or included information

No Comments

No Known Activations