INDEX

Explanations

phrases indicating decision-making processes and their implications

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

web

-0.52

web

-0.42

WEB

-0.42

про

-0.41

но

-0.41

 rzecz

-0.41

 cív

-0.40

here

-0.39

。

-0.38

when

-0.38

POSITIVE LOGITS

AddTagHelper

0.98

Mediabestanden

0.82

 EconPapers

0.80

 saites

0.76

сылкі

0.75

WebElementEntity

0.75

 estekak

0.74

ⓧ

0.74

 yoksa

0.73

ForRow

0.73

Activations Density 0.817%

phrases indicating decision-making processes and their implications

No Comments

No Known Activations