INDEX

Explanations

references to pain and pain-related topics

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

glers

-0.71

 للاسماء

-0.69

stateProvider

-0.68

ViewImports

-0.64

IndentedString

-0.61

เดียว

-0.60

 protoimpl

-0.59

ssohn

-0.59

ariat

-0.58

esModule

-0.58

POSITIVE LOGITS

lessly

0.97

fully

0.84

ful

0.79

staking

0.78

terly

0.69

fulness

0.68

lessness

0.66

 الدولى

0.66

levé

0.64

FULLY

0.63

Activations Density 0.127%

references to pain and pain-related topics

No Comments

No Known Activations