INDEX

Explanations

the prefix "mon" followed by another word

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "mon" 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 @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Norn

-0.83

ORTS

-0.82

IBLE

-0.79

éĹĺ

-0.78

ULTS

-0.76

æĸ¹

-0.75

 Venom

-0.73

UGE

-0.72

å°Ĩ

-0.71

FUL

-0.71

POSITIVE LOGITS

stros

1.39

olith

1.26

olithic

1.23

soon

1.16

ograph

1.15

oton

1.06

ographs

1.05

ocular

1.04

ologue

1.03

omial

1.02

Activations Density 0.016%

the prefix "mon" followed by another word

occurrences of the word "mon" in various contexts

No Comments

No Known Activations