INDEX

Explanations

adjectives ending in 'etic'

oai_token-act-pair · gpt-3.5-turbo

terms related to ethics and moral philosophy

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

äºĶ

-0.72

mberg

-0.72

TAM

-0.70

 Amend

-0.69

ACTED

-0.69

ITNESS

-0.69

ILLE

-0.68

IDENT

-0.68

 Innocent

-0.67

WHERE

-0.67

POSITIVE LOGITS

etic

1.30

ulously

1.22

etics

1.09

etically

1.00

ulous

0.92

aneously

0.91

aneous

0.88

ener

0.86

anism

0.86

luster

0.86

Activations Density 0.006%

adjectives ending in 'etic'

terms related to ethics and moral philosophy

No Comments

No Known Activations