INDEX

Explanations

numerical values related to aggregations

oai_token-act-pair · gpt-3.5-turbo

terms related to the concept of aggregation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

nen

-0.85

nee

-0.84

ockets

-0.83

neys

-0.81

ney

-0.73

ne

-0.72

chen

-0.72

pher

-0.71

ingers

-0.70

anship

-0.70

POSITIVE LOGITS

 aggregate

1.38

 aggreg

1.07

 aggregation

0.93

regate

0.92

 ILCS

0.88

sum

0.79

 antioxid

0.73

 distributions

0.72

 totals

0.70

 averages

0.68

Activations Density 0.005%

numerical values related to aggregations

terms related to the concept of aggregation

No Comments

No Known Activations