INDEX

Explanations

phrases indicating plans or intentions, particularly in a professional context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

now

-0.42

rilla

-0.40

*/),

-0.40

 recently

-0.39

ora

-0.39

 juist

-0.39

 છે

-0.38

gelopen

-0.38

edin

-0.37

 recent

-0.37

POSITIVE LOGITS

 then

0.99

+#+#

0.93

 متعلقه

0.93

 Then

0.93

Then

0.87

then

0.85

 Thereafter

0.83

 nahilalakip

0.82

 سپس

0.81

StoreMessageInfo

0.81

Activations Density 0.363%

phrases indicating plans or intentions, particularly in a professional context

No Comments

No Known Activations