INDEX

Explanations

phrases related to legal entities and professionals

oai_token-act-pair · gpt-3.5-turbo

proper nouns followed by a comma

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

Thumbnail

-0.76

eeds

-0.71

ð

-0.69

":"/

-0.69

izons

-0.69

"]=>

-0.69

Compat

-0.67

enture

-0.67

lings

-0.65

ights

-0.65

POSITIVE LOGITS

 Deborah

1.06

 Jeffrey

1.03

who

1.01

 Jonathan

1.00

who

1.00

 Kathleen

0.99

 Roger

0.99

 Mike

0.99

 Steve

0.98

 Valerie

0.98

Activations Density 0.128%

phrases related to legal entities and professionals

proper nouns followed by a comma

No Comments

No Known Activations