INDEX

Explanations

nonprofit organizations

oai_token-act-pair · gpt-3.5-turbo

mentions of nonprofit organizations

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

othy

-0.81

uncture

-0.76

ussen

-0.75

stroke

-0.74

pler

-0.72

mith

-0.72

amura

-0.71

perature

-0.70

iph

-0.70

Phones

-0.70

POSITIVE LOGITS

 organization

1.01

 corporation

0.99

 organizations

0.98

 fundraising

0.97

 nonprofit

0.94

profit

0.92

 entity

0.91

 organisation

0.90

 funded

0.85

 charitable

0.85

Activations Density 0.033%

nonprofit organizations

mentions of nonprofit organizations

No Comments

No Known Activations