INDEX

Explanations

instances of the word "include" and its variations, indicating a focus on inclusion or additive concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 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

<strong>

-0.54

 fraî

-0.54

mathbf

-0.53

validators

-0.48

 auroit

-0.46

pherds

-0.45

GenerationType

-0.45

ientras

-0.44

Validators

-0.44

farmer

-0.44

POSITIVE LOGITS

 include

1.21

 Include

1.20

include

1.16

Include

1.15

 included

1.13

 inclusion

1.12

 INCLUDE

1.05

 includes

1.05

Included

1.01

 Inclusion

0.99

Activations Density 0.158%

instances of the word "include" and its variations, indicating a focus on inclusion or additive concepts

No Comments

No Known Activations