INDEX

Explanations

terms related to rankings and evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/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.20.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

AnchorStyles

-0.72

webElementXpaths

-0.63

MemoryWarning

-0.63

hysema

-0.52

RenderAtEndOf

-0.52

StoreMessageInfo

-0.51

ある

-0.49

ograma

-0.49

params

-0.47

PropertyChanging

-0.47

POSITIVE LOGITS

notch

1.01

 notch

0.97

TOP

0.94

 Tops

0.86

 tier

0.85

 tops

0.80

Top

0.80

TOP

0.79

 Notch

0.78

most

0.77

Activations Density 0.092%

terms related to rankings and evaluations

No Comments

No Known Activations