INDEX

Explanations

words related to sports competitions and tournaments

oai_token-act-pair · gpt-3.5-turbo

terms related to competitions and tournaments

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

 convictions

-0.66

background

-0.63

enhagen

-0.60

paren

-0.60

spe

-0.60

onom

-0.60

 caves

-0.58

 neut

-0.58

 unpop

-0.58

 aggress

-0.57

POSITIVE LOGITS

hower

1.00

 Lauder

0.85

terday

0.85

DragonMagazine

0.78

ãĤ´ãĥ³

0.78

naire

0.75

âĶĢâĶĢâĶĢâĶĢ

0.74

theless

0.74

 thereof

0.71

enance

0.71

Activations Density 0.152%

words related to sports competitions and tournaments

terms related to competitions and tournaments

No Comments

No Known Activations