INDEX

Explanations

phrases related to providing support and assistance

oai_token-act-pair · gpt-3.5-turbo

conjunctions that link phrases or concepts

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

DX

-0.78

OND

-0.76

Â¶

-0.72

JM

-0.71

Shut

-0.70

DragonMagazine

-0.69

IRD

-0.69

odcast

-0.69

 Powered

-0.69

Morning

-0.67

POSITIVE LOGITS

 thereby

1.50

 thus

1.38

 hence

1.34

 consequently

1.31

 therefore

1.15

 secondly

1.02

 thence

0.97

 furthermore

0.97

 then

0.97

 subsequently

0.95

Activations Density 0.685%

phrases related to providing support and assistance

conjunctions that link phrases or concepts

No Comments

No Known Activations