INDEX

Explanations

phrases or sentences related to being covered, hidden, or surrounded by something

oai_token-act-pair · gpt-3.5-turbo

phrases indicating something "in" or "covered 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

NOW

-0.74

NL

-0.72

TIME

-0.72

FOX

-0.70

DragonMagazine

-0.70

llor

-0.69

oulos

-0.69

ILA

-0.68

ILY

-0.67

afe

-0.67

POSITIVE LOGITS

 accordance

1.01

escap

0.92

 spite

0.88

 vain

0.82

 knots

0.80

 lieu

0.79

clusions

0.79

 Flames

0.75

effic

0.74

 anticipation

0.73

Activations Density 0.134%

phrases or sentences related to being covered, hidden, or surrounded by something

phrases indicating something "in" or "covered in" various contexts

No Comments

No Known Activations