INDEX

Explanations

political affiliations

oai_token-act-pair · gpt-3.5-turbo

key terms related to political affiliations and class distinctions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Travels

-0.67

mun

-0.66

 contagious

-0.62

 Donation

-0.61

 WARN

-0.61

Sno

-0.61

-0.59

 Riley

-0.59

 disclaimer

-0.57

RNA

-0.57

POSITIVE LOGITS

 ones

1.02

itto

0.81

anooga

0.75

 versa

0.75

arge

0.74

bsite

0.73

SPONSORED

0.71

ngth

0.70

 Ones

0.69

 counterpart

0.69

Activations Density 0.517%

political affiliations

key terms related to political affiliations and class distinctions

No Comments

No Known Activations