INDEX

Explanations

specific terms related to various fields or topics

oai_token-act-pair · gpt-3.5-turbo

terms and concepts related to medical clinics, patterns, and structural elements 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 @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãĥ¼ãĥĨ

-0.60

Reason

-0.53

æµ

-0.51

ļé

-0.50

INAL

-0.50

âĸ¬

-0.48

 Azerb

-0.47

 Mald

-0.46

LESS

-0.45

Translation

-0.45

POSITIVE LOGITS

paces

0.92

mith

0.91

hip

0.84

uggest

0.82

linger

0.82

creen

0.81

hooting

0.80

peed

0.80

pace

0.79

chool

0.78

Activations Density 0.854%

specific terms related to various fields or topics

terms and concepts related to medical clinics, patterns, and structural elements in various contexts

No Comments

No Known Activations