INDEX

Explanations

phrases related to different sides or perspectives in a situation

oai_token-act-pair · gpt-3.5-turbo

references to different sides or perspectives in discussions or arguments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

wcs

-0.85

apest

-0.80

dayName

-0.77

ancies

-0.76

 reperto

-0.74

 ILCS

-0.74

Spread

-0.73

RIC

-0.70

>:

-0.68

MSN

-0.67

POSITIVE LOGITS

agons

0.73

 ridge

0.70

 hers

0.67

 aisle

0.65

 fence

0.62

bars

0.62

redo

0.61

 Hudson

0.60

 Highway

0.60

Initialized

0.60

Activations Density 0.097%

phrases related to different sides or perspectives in a situation

references to different sides or perspectives in discussions or arguments

No Comments

No Known Activations