INDEX

Explanations

personal names

oai_token-act-pair · gpt-3.5-turbo

variations of names and titles associated with individuals and roles in government or business contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 versa

-0.69

 Poles

-0.69

 ambassadors

-0.68

 polar

-0.67

 subordinate

-0.65

 Glac

-0.64

 plac

-0.64

 alleg

-0.64

 apex

-0.63

 motif

-0.62

POSITIVE LOGITS

Jr

1.10

ovich

1.07

akis

1.07

owski

0.98

iere

0.95

hoff

0.95

ault

0.92

chuk

0.92

auer

0.90

zynski

0.90

Activations Density 0.479%

personal names

variations of names and titles associated with individuals and roles in government or business contexts

No Comments

No Known Activations