INDEX

Explanations

terms related to airflow and air conditions

oai_token-act-pair · gpt-3.5-turbo

references to air

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

Cla

-0.76

orkshire

-0.72

enance

-0.68

 Barcl

-0.67

Ll

-0.66

llan

-0.66

Kuh

-0.66

 Saur

-0.66

 McKin

-0.64

achu

-0.62

POSITIVE LOGITS

waves

1.14

bnb

1.01

tight

1.01

 conditioning

0.95

planes

0.94

bending

0.92

 turbulence

0.91

plane

0.91

 breat

0.90

 circulation

0.87

Activations Density 0.021%

terms related to airflow and air conditions

references to air

No Comments

No Known Activations