INDEX

Explanations

mentions of specific names, particularly "Henderson" and "Peterson."

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

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

chanind/openwebtext-gemma

Features

16,384

Data Type

float32

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

ctigges/openwebtext-gemma-1024-cl

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-1.49

 autorytatywna

-0.70

+:+

-0.69

McF

-0.69

ɵɵ

-0.67

 Breen

-0.67

Odkazy

-0.66

align

-0.66

 ""],

-0.66

DockStyle

-0.66

POSITIVE LOGITS

 shenan

1.08

 affor

1.05

 depic

1.03

 greate

1.01

 disagre

1.01

 simpsons

1.01

 perfet

1.00

 snoopy

1.00

ftu

1.00

 ftill

0.99

Activations Density 0.191%

mentions of specific names, particularly "Henderson" and "Peterson."

No Comments

No Known Activations