INDEX

Explanations

references to healthcare providers

oai_token-act-pair · gpt-3.5-turbo

references to service providers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

-0.77

schild

-0.74

bum

-0.71

DonaldTrump

-0.69

vim

-0.69

aughs

-0.68

âĸ¬

-0.64

ffen

-0.64

ohan

-0.62

ean

-0.60

POSITIVE LOGITS

 provider

0.92

 providers

0.87

atives

0.81

 Provider

0.78

 licensed

0.77

iders

0.71

nown

0.71

 billing

0.69

 delivering

0.68

 licenses

0.68

Activations Density 0.018%

references to healthcare providers

references to service providers

No Comments

No Known Activations