INDEX

Explanations

phrases related to events happening outside of a location

oai_token-act-pair · gpt-3.5-turbo

mentions of locations or events that occur outside

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

enegger

-0.77

Percent

-0.74

Lay

-0.71

opard

-0.71

lda

-0.70

roo

-0.69

CAST

-0.68

oleon

-0.68

bourg

-0.66

ogun

-0.66

POSITIVE LOGITS

outside

0.82

 diameter

0.80

ntil

0.76

etheless

0.76

 perimeter

0.73

 Outside

0.73

 Indies

0.72

 outside

0.71

 Stamford

0.69

assetsadobe

0.67

Activations Density 0.015%

phrases related to events happening outside of a location

mentions of locations or events that occur outside

No Comments

No Known Activations