INDEX

Explanations

positive attributes or qualities

oai_token-act-pair · gpt-3.5-turbo

words associated with positive qualities or achievements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tf

-0.75

axter

-0.66

igham

-0.65

atson

-0.64

ritz

-0.63

venants

-0.62

Downloadha

-0.61

iless

-0.61

pora

-0.60

tiny

-0.60

POSITIVE LOGITS

 answ

0.76

smanship

0.70

 fodder

0.68

guy

0.68

 throughput

0.67

Sle

0.66

 payoff

0.65

ãĤ®

0.64

 outweigh

0.64

 âĿ

0.63

Activations Density 0.388%

positive attributes or qualities

words associated with positive qualities or achievements

No Comments

No Known Activations