INDEX

Explanations

references to the term "mon" followed by a variation in the subsequent word

oai_token-act-pair · gpt-3.5-turbo

terms related to "mono" structures or concepts, particularly in economic or artistic contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

NRS

-0.83

NRS

-0.81

 Norn

-0.81

ULTS

-0.81

EXP

-0.78

IRO

-0.77

éĹĺ

-0.76

OHN

-0.76

FUL

-0.74

Ranked

-0.72

POSITIVE LOGITS

stros

1.14

olith

1.10

olithic

1.09

oton

0.99

itored

0.97

ocular

0.96

soon

0.95

ials

0.95

ique

0.93

ief

0.92

Activations Density 0.009%

references to the term "mon" followed by a variation in the subsequent word

terms related to "mono" structures or concepts, particularly in economic or artistic contexts

No Comments

No Known Activations