INDEX

Explanations

prepositions and location-related terms

oai_token-act-pair · gpt-3.5-turbo

prepositions and expressions of relationships in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

hement

-0.85

ategory

-0.80

antine

-0.79

hower

-0.69

heastern

-0.67

icularly

-0.66

 nodd

-0.64

icut

-0.64

nor

-0.64

ering

-0.63

POSITIVE LOGITS

 Humanity

0.94

 Noise

0.87

 Hate

0.83

 Geek

0.83

 Represent

0.80

 Extrem

0.78

 Difference

0.77

 Computing

0.76

 Anarch

0.75

 Blind

0.75

Activations Density 0.279%

prepositions and location-related terms

prepositions and expressions of relationships in text

No Comments

No Known Activations