INDEX

Explanations

instances where words related to websites, projects, businesses, products, or creative content are mentioned

oai_token-act-pair · gpt-3.5-turbo

keywords related to websites, businesses, and projects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Juven

-0.67

VIDIA

-0.66

arnaev

-0.63

 Rohing

-0.63

arah

-0.63

 Stern

-0.61

 Lank

-0.61

lash

-0.59

 Samar

-0.59

ead

-0.58

POSITIVE LOGITS

mates

0.98

 selves

0.81

mate

0.81

 mates

0.81

 portfolio

0.80

 holdings

0.74

 counterparts

0.72

 ancestors

0.69

 footprint

0.68

stuff

0.68

Activations Density 0.366%

instances where words related to websites, projects, businesses, products, or creative content are mentioned

keywords related to websites, businesses, and projects

No Comments

No Known Activations