INDEX

Explanations

expressions indicating regret or missed opportunities

oai_token-act-pair · gpt-3.5-turbo

phrases that express a sense of obligation or hindsight

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 maze

-0.83

 veins

-0.72

 transporter

-0.68

hole

-0.67

 opium

-0.66

 centrif

-0.66

 seams

-0.66

fog

-0.65

 Cage

-0.64

axies

-0.64

POSITIVE LOGITS

 someday

0.87

arna

0.81

iners

0.77

ellation

0.75

 emulate

0.71

cipled

0.69

amate

0.69

amation

0.69

×Ļ×

0.67

Recomm

0.67

Activations Density 0.154%

expressions indicating regret or missed opportunities

phrases that express a sense of obligation or hindsight

No Comments

No Known Activations