INDEX

Explanations

mentions of the name "Ann" and context-related references to it

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

-0.54

-0.50

-0.49

Me

-0.49

-0.48

key

-0.48

who

-0.47

-0.46

For

-0.46

-0.45

POSITIVE LOGITS

SequentialGroup

1.05

 Announcement

0.96

 announcement

0.96

 themſelves

0.96

 itſelf

0.95

ſelves

0.93

 فريبيس

0.91

Announcement

0.91

 poffe

0.91

 purpoſe

0.90

Activations Density 0.120%

mentions of the name "Ann" and context-related references to it

No Comments

No Known Activations