INDEX

Explanations

terms related to receiving or being the recipient of something

oai_token-act-pair · gpt-3.5-turbo

instances of the word "received."

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

fall

-0.68

 Quantity

-0.61

 Abyssal

-0.57

Ed

-0.56

flation

-0.55

isting

-0.55

rev

-0.54

 fallacy

-0.53

 Evil

-0.53

 Destroyer

-0.53

POSITIVE LOGITS

dinand

0.89

terson

0.82

DragonMagazine

0.79

imental

0.76

namese

0.75

å¼

0.74

ILY

0.73

sbm

0.72

DAQ

0.70

soever

0.68

Activations Density 0.031%

terms related to receiving or being the recipient of something

instances of the word "received."

No Comments

No Known Activations