INDEX

Explanations

people's names

oai_token-act-pair · gpt-3.5-turbo

common short English words

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

natureconservancy

-0.68

 irrad

-0.67

Downloadha

-0.65

actionDate

-0.63

 coffin

-0.62

stroke

-0.62

 epid

-0.61

ught

-0.61

FACE

-0.60

ModLoader

-0.60

POSITIVE LOGITS

zyk

1.00

osaurus

0.78

Ã©e

0.71

owicz

0.70

 Dynasty

0.70

osaurs

0.69

 Anders

0.69

ois

0.69

 Samar

0.67

opolis

0.67

Activations Density 0.277%

people's names

common short English words

No Comments

No Known Activations