INDEX

Explanations

phrases related to financial transactions like billing and payments

oai_token-act-pair · gpt-3.5-turbo

terms related to billing and financial transactions

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

conserv

-0.79

uther

-0.76

raction

-0.76

JV

-0.75

san

-0.72

ractions

-0.72

itch

-0.66

cest

-0.64

zees

-0.63

Redd

-0.62

POSITIVE LOGITS

 billed

1.04

 billing

1.02

heet

0.84

dule

0.83

 refunds

0.72

payer

0.71

iard

0.70

 reimburse

0.70

 reimb

0.67

ewater

0.65

Activations Density 0.020%

phrases related to financial transactions like billing and payments

terms related to billing and financial transactions

No Comments

No Known Activations