INDEX

Explanations

locations or regions

oai_token-act-pair · gpt-3.5-turbo

references to geographic locations or regions

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

trak

-0.76

CVE

-0.69

ikuman

-0.69

 submar

-0.68

 Scientists

-0.67

Marginal

-0.67

uning

-0.67

BIL

-0.66

 Soda

-0.65

Doctors

-0.62

POSITIVE LOGITS

 globe

0.88

 aisle

0.84

 plains

0.83

 country

0.82

 continent

0.82

 rooft

0.81

country

0.78

 pond

0.76

 breadth

0.76

 continents

0.75

Activations Density 0.097%

locations or regions

references to geographic locations or regions

No Comments

No Known Activations