INDEX

Explanations

terms related to principles of fairness, decency, and equity

oai_token-act-pair · gpt-3.5-turbo

concepts related to fairness and equity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ergy

-0.75

FU

-0.69

oan

-0.66

inis

-0.64

raine

-0.62

aden

-0.62

aining

-0.61

asel

-0.61

ROR

-0.60

arter

-0.60

POSITIVE LOGITS

 fairness

1.07

cipled

0.96

iciary

0.94

 parity

0.92

acies

0.91

parency

0.90

fulness

0.84

ilege

0.83

icial

0.81

cellence

0.80

Activations Density 0.008%

terms related to principles of fairness, decency, and equity

concepts related to fairness and equity

No Comments

No Known Activations