INDEX

Explanations

references to the speaker, emphasizing personal perspective and involvement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 Monfieur

-1.10

Efq

-1.08

 Houſe

-1.04

 ſeveral

-1.02

 '\\;'

-0.97

 ―――――

-0.97

 Conſ

-0.96

 itſelf

-0.96

 houſe

-0.96

 ་་

-0.95

POSITIVE LOGITS

me

2.79

us

1.70

my

1.67

Me

1.65

 myself

1.52

1.37

 Myself

1.36

Me

1.34

myself

1.33

ME

1.33

Activations Density 0.033%

references to the speaker, emphasizing personal perspective and involvement

No Comments

No Known Activations