INDEX

Explanations

words related to complaints or allegations

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>

-2.51

 iyon

-1.10

 guma

-1.08

 maging

-1.06

 silang

-1.03

 hanggang

-0.99

 habang

-0.96

 siyang

-0.96

 makita

-0.96

 muna

-0.95

POSITIVE LOGITS

 stockholm

1.29

 pamph

1.25

 unlaw

1.25

 bordeaux

1.25

 nutella

1.24

 philanth

1.21

 madonna

1.20

 tupperware

1.20

 unden

1.20

 lidl

1.19

Activations Density 0.017%

words related to complaints or allegations

No Comments

No Known Activations