INDEX

Explanations

numerical values and specific years

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/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.10.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

MessageTagHelper

-0.77

zmir

-0.62

 tfsi

-0.61

antaranya

-0.61

 Joplin

-0.58

 "'";

-0.57

 Wenger

-0.57

 Pokies

-0.57

 Spass

-0.57

derry

-0.57

POSITIVE LOGITS

UIControlState

0.76

+#+

0.74

Utf

0.65

ثيق

0.65

writeFieldEnd

0.63

oneph

0.62

diera

0.61

|}{$

0.60

 Salv

0.59

idue

0.59

Activations Density 0.274%

numerical values and specific years

No Comments

No Known Activations