INDEX

Explanations

references to intellectual capabilities and discussions surrounding intellectual themes

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

íma

-0.68

 Fifa

-0.68

 Jameson

-0.68

coltura

-0.68

 Jamestown

-0.67

ecuzione

-0.67

 Salford

-0.67

InputBorder

-0.67

protoimpl

-0.66

InjectMocks

-0.65

POSITIVE LOGITS

 fold

0.86

 intellectual

0.81

serif

0.80

 Intellectual

0.78

 intellectuals

0.76

 bulk

0.75

fold

0.75

Intellectual

0.73

ofold

0.73

 intellectually

0.72

Activations Density 0.052%

references to intellectual capabilities and discussions surrounding intellectual themes

No Comments

No Known Activations