INDEX

Explanations

questions starting with "How can"

oai_token-act-pair · gpt-3.5-turbo

questions that begin with "How can."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

RAFT

-0.70

yssey

-0.68

displayText

-0.67

vez

-0.64

apest

-0.63

 seiz

-0.63

Russ

-0.60

hig

-0.60

 Powered

-0.57

Interstitial

-0.57

POSITIVE LOGITS

't

1.05

berra

1.04

 anyone

0.95

 anybody

0.87

you

0.80

 someone

0.77

 somebody

0.73

we

0.73

 bystanders

0.69

tical

0.67

Activations Density 0.041%

questions starting with "How can"

questions that begin with "How can."

No Comments

No Known Activations