INDEX

Explanations

mentions of "spam" or "spoof."

oai_token-act-pair · gpt-3.5-turbo

occurrences of the substring "sp" in words or phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

âĸ¬âĸ¬

-0.68

 pigeon

-0.62

 purse

-0.61

houses

-0.59

quo

-0.59

 presumptive

-0.59

 guarding

-0.58

 dispatch

-0.58

ĪĴ

-0.57

hon

-0.57

POSITIVE LOGITS

atial

1.38

aghetti

1.37

oiler

1.36

iral

1.28

ooky

1.23

aces

1.21

herical

1.16

inning

1.14

oil

1.13

resso

1.13

Activations Density 0.024%

mentions of "spam" or "spoof."

occurrences of the substring "sp" in words or phrases

No Comments

No Known Activations