INDEX

Explanations

specific years indicated in the text

oai_token-act-pair · gpt-3.5-turbo

dates or years that signify historical milestones or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

Wem

-0.62

 snipp

-0.57

 Wast

-0.54

ashtra

-0.54

Jac

-0.54

imore

-0.53

 Danger

-0.53

 Mens

-0.52

 Fres

-0.52

 Sail

-0.52

POSITIVE LOGITS

 onwards

1.05

 onward

0.94

 inception

0.83

when

0.78

cffffcc

0.74

âĢ²

0.70

 when

0.67

staking

0.67

 until

0.63

maxwell

0.62

Activations Density 0.117%

specific years indicated in the text

dates or years that signify historical milestones or events

No Comments

No Known Activations