INDEX

Explanations

information related to service providers, particularly in different contexts such as healthcare, finance, and technology

oai_token-act-pair · gpt-3.5-turbo

references to providers of services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

yrinth

-0.85

schild

-0.76

bum

-0.72

DonaldTrump

-0.72

aughs

-0.71

vim

-0.71

oria

-0.67

orical

-0.65

ceed

-0.65

ffen

-0.65

POSITIVE LOGITS

 provider

0.96

 providers

0.91

 Provider

0.81

atives

0.80

 licensed

0.79

 specializing

0.70

 licenses

0.70

 beware

0.68

iders

0.67

 services

0.66

Activations Density 0.026%

information related to service providers, particularly in different contexts such as healthcare, finance, and technology

references to providers of services

No Comments

No Known Activations