INDEX

Explanations

occurrences of the word "a" used 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 @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

asticity

-0.52

cur

-0.49

 pris

-0.48

par

-0.47

游

-0.47

BooleanField

-0.46

 сон

-0.46

###############

-0.45

=$((

-0.44

cre

-0.44

POSITIVE LOGITS

TagHelper

0.83

 Chwiliwch

0.82

 wireType

0.75

 Jefus

0.74

 høre

0.74

 Cæsar

0.73

 Anſ

0.72

 TextInputType

0.71

styleType

0.71

 Theſe

0.71

Activations Density 0.115%

occurrences of the word "a" used in various contexts

No Comments

No Known Activations