INDEX

Explanations

names of people or places

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names of people and places

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

 Turtles

-0.86

 Gotham

-0.82

 Grateful

-0.81

 Lovecraft

-0.80

 Freak

-0.80

 Daredevil

-0.79

 superheroes

-0.79

OCD

-0.78

 Wonderland

-0.75

 Luthor

-0.74

POSITIVE LOGITS

awi

1.13

iya

1.03

indu

1.02

aan

1.02

abi

1.01

hani

1.01

hra

0.99

iy

0.99

ema

0.98

arij

0.97

Activations Density 0.414%

names of people or places

proper nouns, particularly names of people and places

No Comments

No Known Activations