INDEX

Explanations

financial terms related to payment or pricing

oai_token-act-pair · gpt-3.5-turbo

references to monetary payments or costs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

yrinth

-0.84

ahime

-0.79

ãĥ¡

-0.74

iframe

-0.74

ãĤ¼ãĤ¦ãĤ¹

-0.68

NetMessage

-0.66

apons

-0.65

aten

-0.65

cn

-0.63

 Canaveral

-0.63

POSITIVE LOGITS

 dues

1.00

 dividends

0.93

 dearly

0.91

 royalties

0.91

 penalty

0.87

 upfront

0.86

 tariff

0.79

 dime

0.78

arations

0.78

 ransom

0.77

Activations Density 0.193%

financial terms related to payment or pricing

references to monetary payments or costs

No Comments

No Known Activations