INDEX

Explanations

references to the ages and demographics of individuals in various contexts

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

her

-0.49

 InputDecoration

-0.46

 مرئيه

-0.45

â

-0.43

 order

-0.43

 déc

-0.43

 fast

-0.42

¿

-0.41

 easy

-0.41

POSITIVE LOGITS

Efq

1.06

 pleaſure

1.04

 Jefus

1.03

 Majefty

1.00

 ſeveral

0.99

 ſtre

0.97

 Monfieur

0.97

 ſtate

0.97

 ſmall

0.96

 Theſe

0.95

Activations Density 0.419%

references to the ages and demographics of individuals in various contexts

No Comments

No Known Activations