INDEX

Explanations

references or descriptions of something being large or significant

oai_token-act-pair · gpt-3.5-turbo

the term "grand," particularly in reference to significant quantities or important contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

lihood

-0.77

 Kers

-0.71

ople

-0.68

qqa

-0.67

utics

-0.66

 Slater

-0.65

phrine

-0.63

PsyNetMessage

-0.63

thia

-0.62

Dialogue

-0.61

POSITIVE LOGITS

parent

1.24

eur

1.19

iosity

1.14

pa

1.12

master

1.11

child

1.10

standing

1.08

father

1.06

mother

1.04

addy

1.03

Activations Density 0.014%

references or descriptions of something being large or significant

the term "grand," particularly in reference to significant quantities or important contexts

No Comments

No Known Activations