INDEX

Explanations

greetings and conversational openings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 dejes

-0.49

 declarat

-0.48

yntaxException

-0.47

 drept

-0.46

 JTextField

-0.46

 aDecoder

-0.45

 muerta

-0.45

quait

-0.45

toHaveBeenCalled

-0.44

const

-0.44

POSITIVE LOGITS

 everyone

1.16

 everybody

1.07

 Everyone

1.04

everyone

0.96

everybody

0.92

 Everybody

0.91

Everyone

0.88

 friends

0.86

 utafitiHapana

0.82

Everybody

0.81

Activations Density 0.069%

greetings and conversational openings

No Comments

No Known Activations