INDEX

Explanations

phrases related to locations, specifically related to the place named "Horn"

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 oliva

-0.59

TextInputLayout

-0.55

paddingVertical

-0.52

paddingLeft

-0.48

tisgarh

-0.48

Angola

-0.47

LayoutStyle

-0.47

Panasonic

-0.46

Život

-0.46

layoutManager

-0.46

POSITIVE LOGITS

 HORN

1.54

 Horn

1.52

 horn

1.51

 Horns

1.49

Horn

1.47

 horns

1.46

 horned

1.27

horn

1.23

Hor

1.00

Hor

1.00

Activations Density 0.137%

phrases related to locations, specifically related to the place named "Horn"

No Comments

No Known Activations