INDEX

Explanations

entities and actions related to politics, terrorism, and technology

oai_token-act-pair · gpt-3.5-turbo

empty sections or non-content in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 obser

-0.66

 glim

-0.63

 Vaugh

-0.60

é¾įå

-0.60

iku

-0.55

Cth

-0.54

Gray

-0.52

âĵĺ

-0.52

 CLIENT

-0.52

 prest

-0.52

POSITIVE LOGITS

zbollah

0.55

 Hillary

0.52

 officially

0.52

 reportedly

0.51

 largeDownload

0.48

 legalized

0.47

 shutdown

0.47

resa

0.47

 indeed

0.46

 banned

0.46

Activations Density 0.611%

entities and actions related to politics, terrorism, and technology

empty sections or non-content in the text

No Comments

No Known Activations