INDEX

Explanations

locations or directions

oai_token-act-pair · gpt-3.5-turbo

geographical directions and locations

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

inventoryQuantity

-1.27

BuyableInstoreAndOnline

-1.21

Ô

-0.89

govtrack

-0.82

ãĥīãĥ©

-0.76

Operation

-0.72

 waivers

-0.70

Viol

-0.69

Prof

-0.67

POSITIVE LOGITS

 coast

0.82

west

0.79

 hemisphere

0.79

iest

0.76

est

0.76

 wing

0.75

 side

0.75

olan

0.75

 Indies

0.75

lake

0.74

Activations Density 0.084%

locations or directions

geographical directions and locations

No Comments

No Known Activations