INDEX

Explanations

keywords related to the term "Lac."

oai_token-act-pair · gpt-3.5-turbo

references to the term "Lac" 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 @ 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

ICE

-0.80

ITNESS

-0.72

icals

-0.71

FTWARE

-0.69

ãĥīãĥ©

-0.67

ãĥĥãĥĪ

-0.66

fulness

-0.65

 Andromeda

-0.62

ittee

-0.62

ãĥĦ

-0.62

POSITIVE LOGITS

rosse

1.27

quer

0.90

Lac

0.88

kered

0.86

uca

0.84

iple

0.84

orem

0.82

ued

0.78

estone

0.78

imar

0.76

Activations Density 0.013%

keywords related to the term "Lac."

references to the term "Lac" in various contexts

No Comments

No Known Activations