INDEX

Explanations

phrases related to rankings and high quality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 فريبيس

-0.74

MockMvc

-0.62

StoreMessageInfo

-0.59

 Exacts

-0.58

webElementXpaths

-0.57

 EconPapers

-0.55

 vôtre

-0.54

postsleuth

-0.54

ಿಸ

-0.54

emang

-0.53

POSITIVE LOGITS

notch

1.03

 notch

1.02

 tier

0.85

most

0.81

 priority

0.79

flight

0.76

 Notch

0.76

ically

0.74

 shelf

0.74

 rated

0.72

Activations Density 0.112%

phrases related to rankings and high quality

No Comments

No Known Activations