INDEX

Explanations

statements about the importance or effectiveness of a subject or idea

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

Diweddarwch

-0.77

 vägen

-0.74

 myſelf

-0.74

 sauvages

-0.72

 becauſe

-0.69

 venons

-0.69

 purpoſe

-0.69

 bezeichneter

-0.68

 itſelf

-0.67

 étan

-0.66

POSITIVE LOGITS

 incumbent

0.55

 natural

0.54

OK

0.52

ngrx

0.51

 ideal

0.49

 للاسماء

0.48

ViewChild

0.48

 certain

0.47

 extra

0.47

une

0.47

Activations Density 0.169%

statements about the importance or effectiveness of a subject or idea

No Comments

No Known Activations