INDEX

Explanations

phrases indicating the significance or prevalence of certain characteristics, outcomes, or behaviors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 both

-0.73

moveToFirst

-0.72

 muitas

-0.72

both

-0.68

 many

-0.67

 sometimes

-0.63

 многих

-0.62

 most

-0.61

 muchas

-0.61

many

-0.61

POSITIVE LOGITS

цездатний

0.73

 comprised

0.73

 consisting

0.72

 devoted

0.71

 consisted

0.70

 consists

0.68

 focused

0.67

 composed

0.65

UserScript

0.65

InitStruct

0.64

Activations Density 0.358%

phrases indicating the significance or prevalence of certain characteristics, outcomes, or behaviors

No Comments

No Known Activations