INDEX

Explanations

phrases inviting to learn more

oai_token-act-pair · gpt-3.5-turbo

phrases related to learning or education

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

peror

-0.69

ordered

-0.68

conn

-0.64

abwe

-0.64

zzi

-0.62

raviolet

-0.62

senal

-0.61

berus

-0.61

amination

-0.60

orescent

-0.59

POSITIVE LOGITS

 lessons

0.83

learn

0.81

 Teach

0.77

lege

0.76

Lear

0.75

 lesson

0.75

 firsthand

0.73

 Curve

0.72

omed

0.72

 humility

0.71

Activations Density 0.029%

phrases inviting to learn more

phrases related to learning or education

No Comments

No Known Activations