INDEX

Explanations

phrases and constructs indicating uncertainty or speculation in discourse

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

imo

-0.55

 يتيمه

-0.51

izarse

-0.49

+/

-0.49

 („

-0.47

egli

-0.47

 Conceptual

-0.47

Rujuakan

-0.46

Vtbl

-0.46

(&

-0.46

POSITIVE LOGITS

tagext

0.84

__*/

0.71

EndGlobalSection

0.70

HtmlAttribute

0.66

AndEndTag

0.62

resave

0.60

enderror

0.58

 ivelany

0.57

 today

0.57

 consultato

0.56

Activations Density 0.157%

phrases and constructs indicating uncertainty or speculation in discourse

No Comments

No Known Activations