INDEX

Explanations

phrases related to definitions or explanations of terms or concepts

oai_token-act-pair · gpt-3.5-turbo

definitions or descriptions of various concepts and terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 Universities

-0.67

 faiths

-0.63

 directions

-0.63

 glaciers

-0.60

selves

-0.60

 Notting

-0.59

 redes

-0.59

 universities

-0.59

 adjustments

-0.59

 shores

-0.59

POSITIVE LOGITS

 ALWAYS

1.06

 usually

0.93

typically

0.92

 preferable

0.87

 always

0.86

 typically

0.86

agine

0.85

someone

0.84

 indistinguishable

0.84

 ordinarily

0.84

Activations Density 0.178%

phrases related to definitions or explanations of terms or concepts

definitions or descriptions of various concepts and terms

No Comments

No Known Activations