INDEX

Explanations

instances where one entity or person is compared to or acting with another entity or person

oai_token-act-pair · gpt-3.5-turbo

references to "the other" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

aram

-0.64

zai

-0.60

aretz

-0.58

abad

-0.57

/"

-0.57

istered

-0.56

ister

-0.56

idential

-0.55

_-

-0.55

POSITIVE LOGITS

worldly

1.59

swer

0.91

parts

0.83

 side

0.77

 hemisphere

0.73

 kindred

0.71

 lobe

0.70

 respects

0.69

wise

0.68

 installments

0.68

Activations Density 0.039%

instances where one entity or person is compared to or acting with another entity or person

references to "the other" in various contexts

No Comments

No Known Activations