INDEX

Explanations

words related to a specific topic or entity, in this case, "Panda."

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "anda," indicating a focus on names or references related to "Anda," such as locations or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

sed

-0.81

kens

-0.67

kes

-0.65

PC

-0.64

 mileage

-0.64

spect

-0.63

ny

-0.63

 Rack

-0.61

 Grind

-0.61

icka

-0.60

POSITIVE LOGITS

emonium

1.33

anda

0.96

wana

0.87

heon

0.82

ahar

0.80

ibo

0.79

onda

0.79

arov

0.78

 Haram

0.78

ani

0.77

Activations Density 0.006%

words related to a specific topic or entity, in this case, "Panda."

mentions of the word "anda," indicating a focus on names or references related to "Anda," such as locations or events

No Comments

No Known Activations