INDEX

Explanations

occurrences of the word "de" 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 @ 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Cæsar

-0.79

 Majefty

-0.65

 Aene

-0.62

TypedDataSet

-0.61

 Oedipus

-0.61

TestingModule

-0.60

 itſelf

-0.59

 Shakspeare

-0.59

 Shaksp

-0.58

 Athenians

-0.57

POSITIVE LOGITS

 course

1.21

course

1.03

COURSE

0.99

 COURSE

0.84

 sorts

0.82

 Course

0.78

the

0.75

Course

0.74

ourse

0.68

 courses

0.66

Activations Density 0.014%

occurrences of the word "de" in various contexts

No Comments

No Known Activations