INDEX

Explanations

mentions of being alone or solitary

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "lone" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

glomer

-0.73

ropri

-0.72

opian

-0.71

ukong

-0.70

raints

-0.69

yrinth

-0.69

 Bulg

-0.65

ends

-0.65

angers

-0.64

 anesthesia

-0.64

POSITIVE LOGITS

 lone

1.03

eteen

0.98

 straw

0.88

 exception

0.82

åŃĲ

0.81

 wolf

0.75

\\\\\\\\\\\\\\\\

0.75

 propriet

0.69

eteenth

0.69

handedly

0.68

Activations Density 0.006%

mentions of being alone or solitary

occurrences of the word "lone" in various contexts

No Comments

No Known Activations