INDEX

Explanations

terms related to literacy and measurement in liters

oai_token-act-pair · gpt-3.5-turbo

terms related to literacy and its various forms

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

 Sands

-0.83

Ĥª

-0.69

swer

-0.64

cffffcc

-0.63

 palms

-0.63

bones

-0.61

 relaxing

-0.61

-0.59

EEP

-0.59

EA

-0.59

POSITIVE LOGITS

atures

1.19

acy

1.12

uania

1.07

acies

1.06

ature

1.03

umen

0.95

liter

0.95

 liter

0.91

naire

0.91

iculture

0.88

Activations Density 0.010%

terms related to literacy and measurement in liters

terms related to literacy and its various forms

No Comments

No Known Activations