INDEX

Explanations

instances where someone holds a specific position or duty

oai_token-act-pair · gpt-3.5-turbo

phrases that describe roles or positions held by individuals

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

ongyang

-0.70

itational

-0.67

ople

-0.66

rax

-0.66

usra

-0.64

fab

-0.62

fy

-0.62

raq

-0.61

rir

-0.61

reau

-0.60

POSITIVE LOGITS

pired

1.10

pires

0.94

 regards

0.94

 well

0.92

 opposed

0.86

bestos

0.83

 evidenced

0.80

piring

0.80

pire

0.73

 stewards

0.72

Activations Density 0.159%

instances where someone holds a specific position or duty

phrases that describe roles or positions held by individuals

No Comments

No Known Activations