INDEX

Explanations

adjectives with negative connotations

oai_token-act-pair · gpt-3.5-turbo

terms related to negative or harsh descriptors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 ethics

-0.67

FU

-0.64

OTA

-0.60

 Uganda

-0.59

ENE

-0.58

 Matter

-0.58

RI

-0.58

MU

-0.58

ANS

-0.57

tions

-0.56

POSITIVE LOGITS

uously

1.22

uous

1.21

ingly

1.20

htaking

1.12

igious

1.04

ctic

1.01

amental

0.98

acular

0.96

herent

0.96

uable

0.96

Activations Density 0.095%

adjectives with negative connotations

terms related to negative or harsh descriptors

No Comments

No Known Activations