INDEX

Explanations

direct or indirect requests or calls to action

oai_token-act-pair · gpt-3.5-turbo

imperative phrases that suggest requesting information or inquiries

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

Ĥ¬

-0.75

cutting

-0.73

rongh

-0.68

rient

-0.67

ffen

-0.66

pite

-0.66

lim

-0.65

swing

-0.65

zinski

-0.65

abama

-0.64

POSITIVE LOGITS

naires

1.09

 questions

1.02

 rhet

1.01

 probing

0.95

wered

0.87

 asked

0.86

 answered

0.83

 answ

0.82

erville

0.81

 politely

0.80

Activations Density 0.047%

direct or indirect requests or calls to action

imperative phrases that suggest requesting information or inquiries

No Comments

No Known Activations