INDEX

Explanations

quantitative data related to various categories such as economy, agriculture, and taxes

oai_token-act-pair · gpt-3.5-turbo

instances of the phrase "In" followed by numerical data or statistics

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ingred

-0.77

 haun

-0.64

 behav

-0.64

 disapp

-0.63

 medd

-0.63

 enthus

-0.63

 nurt

-0.62

 haunt

-0.61

Enlarge

-0.60

enance

-0.59

POSITIVE LOGITS

 addition

1.47

 comparison

1.46

 contrast

1.40

flation

1.27

cluding

1.25

ventory

1.24

juries

1.22

 terms

1.18

 total

1.12

jury

1.05

Activations Density 0.111%

quantitative data related to various categories such as economy, agriculture, and taxes

instances of the phrase "In" followed by numerical data or statistics

No Comments

No Known Activations