INDEX

Explanations

terms related to job titles and positions of authority

oai_token-act-pair · gpt-3.5-turbo

titles and positions of authority or leadership

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 notions

-0.67

 differe

-0.64

mug

-0.63

 blister

-0.62

 labels

-0.59

ushes

-0.59

gotten

-0.58

 myths

-0.58

 strangers

-0.57

 surprises

-0.57

POSITIVE LOGITS

 overseeing

1.08

esses

0.83

chief

0.76

ess

0.76

 alongside

0.76

 Assist

0.76

 extraord

0.74

/#

0.74

ature

0.72

 apprentice

0.72

Activations Density 0.226%

terms related to job titles and positions of authority

titles and positions of authority or leadership

No Comments

No Known Activations