INDEX

Explanations

occurrences of certain keywords and phrases, including specific names or titles indicating importance or relevance in a context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

-0.63

-0.61

-0.60

in

-0.59

-0.58

is

-0.57

for

-0.57

to

-0.55

POSITIVE LOGITS

Efq

1.56

 itſelf

1.43

ſelf

1.43

 myſelf

1.42

ſelves

1.40

 Jefus

1.38

 ſeveral

1.25

 Houſe

1.23

 houſe

1.21

 Majefty

1.19

Activations Density 0.758%

occurrences of certain keywords and phrases, including specific names or titles indicating importance or relevance in a context

No Comments

No Known Activations