INDEX

Explanations

phrases related to fairness and safety

oai_token-act-pair · gpt-3.5-turbo

concepts related to fairness and safety in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

okia

-0.78

staking

-0.71

chini

-0.69

UA

-0.67

nik

-0.67

 Puzzles

-0.67

akov

-0.66

layer

-0.66

 Soup

-0.65

 Dreams

-0.65

POSITIVE LOGITS

 orderly

1.44

 equitable

1.40

 prosperous

1.32

 sustainable

1.28

 stable

1.28

 secure

1.28

 balanced

1.28

 efficient

1.26

 inclusive

1.25

 resilient

1.23

Activations Density 0.121%

phrases related to fairness and safety

concepts related to fairness and safety in various contexts

No Comments

No Known Activations