INDEX

Explanations

phrases including the word "community"

oai_token-act-pair · gpt-3.5-turbo

instances of the substring "com" within words

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

 Krug

-0.63

 Wilde

-0.63

 Refuge

-0.63

 steroids

-0.62

AFL

-0.59

 recall

-0.59

 Ducks

-0.59

-0.58

 Wings

-0.57

 Flan

-0.57

POSITIVE LOGITS

pleted

1.31

fortable

1.27

puters

1.26

pleting

1.13

pletion

1.11

puting

1.10

mitted

1.02

mented

0.99

edy

0.97

parable

0.96

Activations Density 0.024%

phrases including the word "community"

instances of the substring "com" within words

No Comments

No Known Activations