INDEX

Explanations

specific names or names of organizations

oai_token-act-pair · gpt-3.5-turbo

proper nouns and specific entities throughout the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ãĥ¼ãĥĨãĤ£

-0.54

Tenn

-0.51

ZI

-0.50

joining

-0.50

 Newtown

-0.50

 Ulster

-0.49

 Burg

-0.49

Kiw

-0.49

 Tenn

-0.48

-0.47

POSITIVE LOGITS

 consisted

0.75

 consists

0.68

 itself

0.67

 comprises

0.59

 reportedly

0.59

is

0.58

 smelled

0.58

 cannot

0.57

 refers

0.57

 herself

0.57

Activations Density 0.729%

specific names or names of organizations

proper nouns and specific entities throughout the text

No Comments

No Known Activations