INDEX

Explanations

references to the letter "D" followed by a single digit

oai_token-act-pair · gpt-3.5-turbo

the letter "D" 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 @ 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

ãĤ¡

-0.83

terday

-0.81

 Bulg

-0.80

 Canaver

-0.71

 lett

-0.71

 Isles

-0.70

EStream

-0.68

ierrez

-0.68

éĹĺ

-0.67

 Ascension

-0.66

POSITIVE LOGITS

etermin

1.17

etermined

1.16

etermination

1.16

aughters

1.13

ownt

1.12

azz

1.07

orm

1.07

agon

1.06

erm

1.04

olph

1.04

Activations Density 0.048%

references to the letter "D" followed by a single digit

the letter "D" in various contexts

No Comments

No Known Activations