INDEX

Explanations

the word "acer" in various contexts

oai_token-act-pair · gpt-3.5-turbo

words related to locations or places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

isSpecialOrderable

-0.73

soDeliveryDate

-0.70

ĸļ

-0.64

elf

-0.62

CHA

-0.62

 unanimous

-0.60

Keefe

-0.60

 perverse

-0.60

 Fighters

-0.60

 neighbouring

-0.57

POSITIVE LOGITS

oute

1.36

acer

1.35

acers

1.10

itech

1.01

ican

0.90

anu

0.86

ica

0.83

icans

0.83

oad

0.82

iser

0.79

Activations Density 0.008%

the word "acer" in various contexts

words related to locations or places

No Comments

No Known Activations