INDEX

Explanations

questions starting with "What is"

oai_token-act-pair · gpt-3.5-turbo

questions that begin with "What is" or "What are."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

iae

-0.68

toe

-0.67

osi

-0.66

oso

-0.65

iences

-0.65

opez

-0.65

 mills

-0.63

 refrain

-0.62

hedon

-0.62

hens

-0.62

POSITIVE LOGITS

 happening

0.94

Ĥª

0.76

omorphic

0.75

?".

0.72

 meant

0.72

?,

0.70

???

0.68

?",

0.68

?]

0.68

?????

0.67

Activations Density 0.043%

questions starting with "What is"

questions that begin with "What is" or "What are."

No Comments

No Known Activations