INDEX

Explanations

proper nouns, specifically names of individuals and institutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/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.21.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

AndEndTag

-0.87

setVerticalGroup

-0.62

enterOuterAlt

-0.59

دانشنامهٔ

-0.54

hObject

-0.54

createCanvas

-0.52

✨:

-0.52

 remplir

-0.49

hawatir

-0.48

الحياه

-0.47

POSITIVE LOGITS

 actionMode

0.56

("")]

0.55

ogenes

0.54

zegorz

0.54

InstanceState

0.53

 effusion

0.53

 Permalink

0.52

 whips

0.52

Rhestr

0.51

 Quant

0.51

Activations Density 0.207%

proper nouns, specifically names of individuals and institutions

No Comments

No Known Activations