INDEX

Explanations

phrases related to locations or entities impacted by certain actions or events

oai_token-act-pair · gpt-3.5-turbo

key terms related to governance and jurisdiction

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

Dialog

-0.70

 Scient

-0.63

Marginal

-0.61

 Izan

-0.59

fits

-0.58

'/

-0.57

 Ends

-0.57

'?

-0.56

 Starts

-0.55

!:

-0.54

POSITIVE LOGITS

 have

1.11

are

1.10

 insist

1.08

 contend

1.04

 were

1.04

 prefer

1.01

 argue

1.01

 reacted

0.99

 aren

0.95

owe

0.94

Activations Density 0.575%

phrases related to locations or entities impacted by certain actions or events

key terms related to governance and jurisdiction

No Comments

No Known Activations