INDEX

Explanations

phrases related to obtaining or not obtaining something

oai_token-act-pair · gpt-3.5-turbo

the word "get" and its variations used in various contexts

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

 Archdemon

-0.66

 Lens

-0.59

some

-0.56

idian

-0.55

haus

-0.55

ont

-0.55

 Lange

-0.54

 backdrop

-0.53

 Tanz

-0.53

 Britann

-0.53

POSITIVE LOGITS

rid

1.07

 bored

0.97

tin

0.96

 punished

0.93

 fooled

0.91

 distracted

0.90

cha

0.89

 sucked

0.89

 offended

0.88

 caught

0.88

Activations Density 0.097%

phrases related to obtaining or not obtaining something

the word "get" and its variations used in various contexts

No Comments

No Known Activations