INDEX

Explanations

words related to unfairness, unjust actions, and unjust conditions

oai_token-act-pair · gpt-3.5-turbo

terms related to injustice and unfairness

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

rians

-0.74

ership

-0.74

gdala

-0.70

phrine

-0.69

 Budd

-0.68

rose

-0.68

ynthesis

-0.68

natureconservancy

-0.68

ournals

-0.68

 VIDEOS

-0.64

POSITIVE LOGITS

 burden

1.00

 discrimination

0.96

 prejudice

0.96

 disadvantage

0.95

 discriminatory

0.94

 burdens

0.94

 dismissal

0.93

 unfair

0.93

 retaliation

0.92

 punishment

0.92

Activations Density 0.098%

words related to unfairness, unjust actions, and unjust conditions

terms related to injustice and unfairness

No Comments

No Known Activations