INDEX

Explanations

phrases related to user accounts in digital platforms

oai_token-act-pair · gpt-3.5-turbo

references to user accounts 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 @ 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

 Sight

-0.72

GGGGGGGG

-0.68

 wings

-0.66

Îµ

-0.64

leys

-0.64

borough

-0.64

ãĥķãĤ©

-0.64

ãĤ¬

-0.64

 spur

-0.63

hua

-0.63

POSITIVE LOGITS

ancy

1.34

 balances

1.08

ants

0.98

 holder

0.96

abilities

0.94

 rece

0.92

 holders

0.91

 credentials

0.91

ership

0.89

Account

0.88

Activations Density 0.019%

phrases related to user accounts in digital platforms

references to user accounts in various contexts

No Comments

No Known Activations