INDEX

Explanations

phrases where a reason is given for something

oai_token-act-pair · gpt-3.5-turbo

the word "because" and its use 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

thal

-0.65

Eye

-0.62

 sideline

-0.61

yan

-0.60

shaw

-0.58

Luc

-0.58

Bear

-0.58

robe

-0.58

mint

-0.57

lean

-0.57

POSITIVE LOGITS

*/(

0.92

assetsadobe

0.83

govtrack

0.76

endment

0.74

uration

0.72

akening

0.72

xual

0.70

udo

0.69

liga

0.68

oku

0.68

Activations Density 0.062%

phrases where a reason is given for something

the word "because" and its use in various contexts

No Comments

No Known Activations