INDEX

Explanations

proper nouns or specific terms/phrases

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate examples or specifications of previously mentioned concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 tears

-0.58

ou

-0.58

ater

-0.57

 next

-0.56

ickets

-0.55

 luck

-0.55

im

-0.55

imeter

-0.54

ort

-0.54

imming

-0.53

POSITIVE LOGITS

 namely

3.95

viz

2.53

 Firstly

1.45

 secondly

1.42

 notably

1.42

ie

1.35

 Specifically

1.28

 whereby

1.26

 Including

1.23

 albeit

1.19

Activations Density 0.009%

proper nouns or specific terms/phrases

phrases that indicate examples or specifications of previously mentioned concepts

No Comments

No Known Activations