INDEX

Explanations

prepositions followed by locations or actions

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "in."

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

onym

-0.80

WER

-0.68

 publishes

-0.67

%%

-0.66

arnaev

-0.63

 authors

-0.62

 lett

-0.61

killed

-0.61

dor

-0.61

eteria

-0.60

POSITIVE LOGITS

 favor

1.14

jury

1.11

 lieu

1.03

 favour

1.02

juries

1.00

ordinate

0.96

 unison

0.95

 tandem

0.95

animate

0.95

offensive

0.93

Activations Density 0.227%

prepositions followed by locations or actions

occurrences of the word "in."

No Comments

No Known Activations