INDEX

Explanations

phrases and terms related to positive attributes or qualities, particularly emphasizing charm

oai_token-act-pair · gpt-3.5-turbo

words related to charm and charisma

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

arians

-0.82

alez

-0.69

©¶æ

-0.68

arers

-0.66

ffic

-0.65

ettel

-0.62

ferred

-0.62

orters

-0.60

 GPUs

-0.60

akening

-0.60

POSITIVE LOGITS

 charm

1.21

 charms

1.03

isma

0.90

ingly

0.89

trap

0.79

 charisma

0.78

 charming

0.76

 Charm

0.76

 lure

0.76

ogue

0.75

Activations Density 0.011%

phrases and terms related to positive attributes or qualities, particularly emphasizing charm

words related to charm and charisma

No Comments

No Known Activations