INDEX

Explanations

phrases expressing proximity or closeness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

Bibliographie

-0.65

ագրություններ

-0.61

]--;

-0.61

InitVars

-0.57

lemented

-0.57

jsoup

-0.57

autorest

-0.56

 Rudd

-0.55

badi

-0.54

 zewnętrzne

-0.53

POSITIVE LOGITS

 close

1.28

 closer

1.24

 near

1.21

near

1.20

 Near

1.17

 nearer

1.17

Near

1.13

 proximity

1.12

接近

1.08

 نزدیک

1.07

Activations Density 0.216%

phrases expressing proximity or closeness

No Comments

No Known Activations