INDEX

Explanations

instances of the word "Nor" followed by a number

oai_token-act-pair · gpt-3.5-turbo

the name "Nor" frequently mentioned 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 @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

AGES

-0.72

ULT

-0.70

AGE

-0.69

ItemImage

-0.69

aging

-0.64

ulate

-0.63

place

-0.62

 cavity

-0.62

ULAR

-0.61

FTA

-0.60

POSITIVE LOGITS

berto

1.00

nir

0.95

wegian

0.93

phan

0.93

rien

0.92

withstanding

0.90

wich

0.88

quist

0.87

stad

0.86

pheus

0.84

Activations Density 0.008%

instances of the word "Nor" followed by a number

the name "Nor" frequently mentioned in various contexts

No Comments

No Known Activations