INDEX

Explanations

mentions of monthly payment amounts

oai_token-act-pair · gpt-3.5-turbo

references to monthly pricing or subscription 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

tty

-0.69

ierrez

-0.69

monton

-0.67

 Aires

-0.67

oken

-0.67

urtles

-0.67

gewater

-0.67

alus

-0.66

ryan

-0.66

acebook

-0.65

POSITIVE LOGITS

ago

0.74

 attRot

0.71

 increments

0.71

offset

0.70

cakes

0.68

Month

0.66

Market

0.65

 duration

0.65

 thereafter

0.64

 intervals

0.64

Activations Density 0.014%

mentions of monthly payment amounts

references to monthly pricing or subscription costs

No Comments

No Known Activations