INDEX

Explanations

phrases indicating future actions or events

oai_token-act-pair · gpt-3.5-turbo

the auxiliary verb "have" 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

 rumor

-0.62

osi

-0.62

 guiName

-0.59

 wounding

-0.59

andan

-0.58

 bribe

-0.58

 trope

-0.57

ensing

-0.57

 mash

-0.57

 disguise

-0.55

POSITIVE LOGITS

 been

1.02

 gotten

0.97

 taken

0.84

 seen

0.84

 undergone

0.83

 eaten

0.83

 gone

0.82

drawn

0.81

been

0.79

gotten

0.79

Activations Density 0.071%

phrases indicating future actions or events

the auxiliary verb "have" in various contexts

No Comments

No Known Activations