INDEX

Explanations

phrases indicating addition or stacking

oai_token-act-pair · gpt-3.5-turbo

phrases that emphasize hierarchical or sequential relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

iment

-0.68

 Cosponsors

-0.63

 shorten

-0.59

ischer

-0.59

ANS

-0.58

more

-0.58

aren

-0.57

ern

-0.57

worst

-0.56

 moderators

-0.56

POSITIVE LOGITS

paying

0.72

 steroids

0.66

ĺħ

0.64

 ours

0.64

rolet

0.62

 Vulkan

0.62

 hers

0.61

oxide

0.61

 suspending

0.59

standing

0.59

Activations Density 0.057%

phrases indicating addition or stacking

phrases that emphasize hierarchical or sequential relationships

No Comments

No Known Activations