INDEX

Explanations

information related to conditions and consequences surrounding actions or situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

Than

-0.59

Kontrola

-0.57

ByExample

-0.51

bootstrapcdn

-0.50

DeleteMapping

-0.50

]")]

-0.50

than

-0.49

anément

-0.48

 Than

-0.48

ComponentModel

-0.48

POSITIVE LOGITS

 يتيمه

0.69

 nahilalakip

0.60

 dabei

0.60

 RouterModule

0.58

yorsunuz

0.57

 izan

0.56

tadır

0.55

 obstante

0.54

ContentAsync

0.54

íně

0.54

Activations Density 0.435%

information related to conditions and consequences surrounding actions or situations

No Comments

No Known Activations