INDEX

Explanations

words related to companies and organizations

oai_token-act-pair · gpt-3.5-turbo

mentions of companies or organizational entities

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 positives

-0.80

 shocks

-0.72

 regrets

-0.71

 quotations

-0.70

 reminders

-0.67

 confirmation

-0.64

 doors

-0.61

 prompts

-0.61

 veins

-0.61

 projectiles

-0.60

POSITIVE LOGITS

 called

1.76

 Called

1.64

called

1.55

 named

1.41

 dubbed

1.38

 termed

1.37

named

1.34

 known

1.33

 titled

1.26

 nicknamed

1.22

Activations Density 1.154%

words related to companies and organizations

mentions of companies or organizational entities

No Comments

No Known Activations