INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

phrases that frequently include the word "the."

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

haps

-0.69

opus

-0.68

berus

-0.68

ãĤ´ãĥ³

-0.67

olo

-0.65

omever

-0.64

abba

-0.64

SPONSORED

-0.64

imaru

-0.63

yet

-0.63

POSITIVE LOGITS

 latter

0.95

 aforementioned

0.88

 greatest

0.83

 biggest

0.83

 strongest

0.80

 same

0.79

 applicant

0.79

 toughest

0.79

ses

0.79

 deadliest

0.78

Activations Density 0.162%

proper nouns

phrases that frequently include the word "the."

No Comments

No Known Activations