INDEX

Explanations

words related to individuals who have graduated from an educational institution

oai_token-act-pair · gpt-3.5-turbo

references to alumni and their impact or involvement

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

lihood

-0.68

erness

-0.65

plays

-0.65

 Simple

-0.62

 Nightmares

-0.60

 Printed

-0.60

 Simulator

-0.60

baby

-0.59

Simple

-0.59

 Robot

-0.59

POSITIVE LOGITS

umni

1.14

uates

1.10

 alumni

1.05

olor

0.85

uate

0.82

rities

0.82

 alum

0.79

Reviewer

0.76

lia

0.74

ulty

0.74

Activations Density 0.020%

words related to individuals who have graduated from an educational institution

references to alumni and their impact or involvement

No Comments

No Known Activations