INDEX

Explanations

expressions indicating possession or experience

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

the

-0.75

-0.65

an

-0.59

 these

-0.54

WindowListener

-0.50

 what

-0.50

all

-0.49

jo

-0.48

 this

-0.47

POSITIVE LOGITS

rrggbb

0.81

RenderAtEndOf

0.81

tvguidetime

0.79

)_/¯

0.73

wahati

0.69

 Roskov

0.68

\{\\

0.68

EDEFAULT

0.67

 photolibrary

0.64

AccessFile

0.62

Activations Density 0.145%

expressions indicating possession or experience

No Comments

No Known Activations