INDEX

Explanations

past tense verbs indicating actions or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

клопе

-0.57

Personendaten

-0.54

 DIFFER

-0.54

Documented

-0.53

isure

-0.51

 yaptı

-0.50

uggets

-0.49

 HAPPENED

-0.49

 EconPapers

-0.49

 ranchers

-0.48

POSITIVE LOGITS

Iba

0.60

XmlAccessType

0.59

 CreateTagHelper

0.54

InjectAttribute

0.54

cjon

0.51

 ursprünglich

0.51

."*

0.50

 hoped

0.50

 Strahl

0.49

 createDate

0.49

Activations Density 0.465%

past tense verbs indicating actions or events

No Comments

No Known Activations