INDEX

Explanations

detailed descriptions or analysis

oai_token-act-pair · gpt-3.5-turbo

concepts related to alternative perspectives and transformations in thought or situation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 cabinets

-0.75

azines

-0.69

 Annotations

-0.68

inventoryQuantity

-0.67

enting

-0.65

olation

-0.62

 Unloaded

-0.61

ebook

-0.60

 bowls

-0.60

inders

-0.59

POSITIVE LOGITS

%:

0.78

]:

0.77

 hitch

0.70

 namely

0.67

:]

0.65

:[

0.64

:#

0.63

 unsus

0.63

\":

0.62

 caveat

0.62

Activations Density 0.657%

detailed descriptions or analysis

concepts related to alternative perspectives and transformations in thought or situation

No Comments

No Known Activations