INDEX

Explanations

mentions of specific locations within a building or structure

oai_token-act-pair · gpt-3.5-turbo

prepositional phrases indicating location or context

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

Äĩ

-0.82

amount

-0.81

ãĤ¼ãĤ¦ãĤ¹

-0.75

ÃŁ

-0.71

arella

-0.70

>(

-0.70

REF

-0.68

merga

-0.68

 amount

-0.66

phabet

-0.64

POSITIVE LOGITS

 Ideal

0.70

 Stamford

0.70

 Parliament

0.67

 unsuspecting

0.67

 Genius

0.67

 courthouse

0.66

Mt

0.66

 Notre

0.64

Sty

0.64

 CafÃ©

0.64

Activations Density 0.191%

mentions of specific locations within a building or structure

prepositional phrases indicating location or context

No Comments

No Known Activations