INDEX

Explanations

terms related to private entities

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

WriteTagHelper

-0.69

 noqa

-0.66

GEBURTS

-0.65

 Itself

-0.65

 disponibilités

-0.64

AndEndTag

-0.64

 InputDecoration

-0.62

clable

-0.61

INCREF

-0.60

 cref

-0.60

POSITIVE LOGITS

 sector

0.88

sector

0.70

Sector

0.70

 SECTOR

0.69

 Sector

0.68

Private

0.65

 cittadini

0.64

PRIVATE

0.62

 Private

0.61

::::::::::::::::

0.58

Activations Density 0.063%

terms related to private entities

No Comments

No Known Activations