INDEX

Explanations

phrases related to predictions and suggestions

oai_token-act-pair · gpt-3.5-turbo

instances of empty text or the absence of content

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

stood

-0.83

 Seym

-0.77

 Azerb

-0.70

accompan

-0.68

edIn

-0.68

ilaterally

-0.63

 Vaugh

-0.63

neath

-0.62

 nearest

-0.59

Reason

-0.59

POSITIVE LOGITS

CRIPTION

0.66

0.63

Psy

0.60

].

0.58

zbollah

0.57

hift

0.56

atem

0.55

];

0.55

 prompt

0.54

 Tradable

0.53

Activations Density 0.045%

phrases related to predictions and suggestions

instances of empty text or the absence of content

No Comments

No Known Activations