INDEX

Explanations

references to vehicles being parked

oai_token-act-pair · gpt-3.5-turbo

references to parked vehicles

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

 Flavoring

-0.98

é¾įå¥ĳå£«

-0.73

bit

-0.71

BIT

-0.71

bits

-0.68

mp

-0.67

bern

-0.66

metic

-0.64

inventoryQuantity

-0.63

urgical

-0.62

POSITIVE LOGITS

 parked

0.91

CLASSIFIED

0.77

 atop

0.74

river

0.71

 beside

0.70

atoon

0.69

 buggy

0.68

 somewhere

0.68

entary

0.68

 innoc

0.66

Activations Density 0.059%

references to vehicles being parked

references to parked vehicles

No Comments

No Known Activations