INDEX

Explanations

references to the name "Karen" and instances of the word "handed."

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

in

-0.52

sep

-0.49

ac

-0.49

name

-0.47

ss

-0.46

-0.45

lan

-0.45

POSITIVE LOGITS

twimg

1.16

 Roskov

1.05

GEBURTSDATUM

1.03

tagHelperRunner

1.02

^(@)

1.01

fjspx

1.00

Билгалдахарш

1.00

 ExecuteAsync

0.98

matchCondition

0.98

UnusedPrivate

0.94

Activations Density 0.140%

references to the name "Karen" and instances of the word "handed."

No Comments

No Known Activations