INDEX

Explanations

instances of the first-person pronoun "I" and variations of it

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 their

-0.59

 avulla

-0.58

 محفوظة

-0.57

hetti

-0.53

ammans

-0.53

 getStart

-0.53

RenderAtEndOf

-0.52

 users

-0.51

TemporalType

-0.51

jų

-0.51

POSITIVE LOGITS

my

1.34

 myself

1.18

1.15

 meines

1.08

my

1.05

My

1.02

 meus

1.00

 meiner

0.99

我

0.99

Activations Density 0.386%

instances of the first-person pronoun "I" and variations of it

No Comments

No Known Activations