INDEX

Explanations

instances of the word "where"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 myſelf

-1.50

 Monfieur

-1.44

 Reſ

-1.43

 Jefus

-1.43

Efq

-1.40

 itſelf

-1.39

 Anſ

-1.38

 Theſe

-1.38

 ―――――

-1.35

ſelf

-1.33

POSITIVE LOGITS

 which

1.77

 where

1.69

 wherein

1.26

 whose

1.25

 that

1.20

 whereby

1.18

 when

1.15

 donde

1.05

 hvor

1.04

 dimana

1.04

Activations Density 0.240%

instances of the word "where"

No Comments

No Known Activations