INDEX

Explanations

location names

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names and brands

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

©¶æ¥µ

-0.60

URA

-0.56

Ble

-0.56

 congr

-0.52

 Sarah

-0.52

âĸĵ

-0.51

 Becky

-0.51

 Sheffield

-0.51

 Nikki

-0.51

BLIC

-0.51

POSITIVE LOGITS

udos

0.71

ahime

0.66

escription

0.66

ancers

0.64

hyde

0.64

ees

0.63

raine

0.62

ulent

0.62

otin

0.61

chuk

0.61

Activations Density 0.463%

location names

proper nouns, particularly names and brands

No Comments

No Known Activations