INDEX

Explanations

phrases or expressions indicating approval or acknowledgment

oai_token-act-pair · gpt-3.5-turbo

instances of the word "nod" and its variations indicating agreement or acknowledgment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

inventoryQuantity

-0.85

 tabl

-0.71

OTOS

-0.69

 Tycoon

-0.68

ÄŁ

-0.67

 Hebdo

-0.66

à¦

-0.64

ãĥł

-0.63

izoph

-0.61

Cov

-0.61

POSITIVE LOGITS

ules

1.09

atory

1.07

nod

1.03

emonic

1.02

ule

0.97

vironment

0.95

ename

0.95

emon

0.94

endum

0.91

enary

0.88

Activations Density 0.031%

phrases or expressions indicating approval or acknowledgment

instances of the word "nod" and its variations indicating agreement or acknowledgment

No Comments

No Known Activations