INDEX

Explanations

words related to low quality or risky financial investments

oai_token-act-pair · gpt-3.5-turbo

references to "junk" and "junk" ratings or classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

voy

-0.70

 unintended

-0.68

 Verge

-0.64

APH

-0.64

BOOK

-0.60

 Scarlett

-0.59

 brim

-0.56

 displeasure

-0.56

 expressive

-0.56

tti

-0.55

POSITIVE LOGITS

buster

1.10

irk

1.08

ies

1.04

rat

0.97

alos

0.96

ett

0.95

etsu

0.93

unks

0.91

vertisement

0.91

regate

0.91

Activations Density 0.074%

words related to low quality or risky financial investments

references to "junk" and "junk" ratings or classifications

No Comments

No Known Activations