INDEX

Explanations

phrases indicating limited or minimal knowledge or impact

oai_token-act-pair · gpt-3.5-turbo

phrases indicating a lack of knowledge or uncertainty

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

ONSORED

-0.70

 Gate

-0.66

hovah

-0.64

 eleph

-0.63

[|

-0.62

 domin

-0.61

AST

-0.58

 Bundes

-0.58

ettings

-0.57

aughters

-0.56

POSITIVE LOGITS

¬¼

0.78

ibaba

0.73

shed

0.73

bur

0.68

pace

0.68

 trickle

0.67

enough

0.67

ptive

0.66

WARE

0.65

pocket

0.65

Activations Density 0.113%

phrases indicating limited or minimal knowledge or impact

phrases indicating a lack of knowledge or uncertainty

No Comments

No Known Activations