INDEX

Explanations

references to the word "it" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 Majefty

-0.95

 himſelf

-0.87

 raiſ

-0.86

 Monfieur

-0.86

 Houſe

-0.85

 myſelf

-0.84

 houſe

-0.84

 poffe

-0.84

 ſtate

-0.81

 whoſe

-0.79

POSITIVE LOGITS

It

0.68

 wasn

0.67

It

0.60

it

0.60

Wasn

0.57

 wouldn

0.56

 quoi

0.56

The

0.54

ça

0.54

playSound

0.54

Activations Density 0.153%

references to the word "it" in various contexts

No Comments

No Known Activations