INDEX

Explanations

locations or settings within a sentence

oai_token-act-pair · gpt-3.5-turbo

prepositions and their occurrences in various contexts

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

NOW

-0.63

CLASSIFIED

-0.61

BUS

-0.61

 booked

-0.60

MORE

-0.60

 debuted

-0.59

0000000000000000

-0.59

 bolted

-0.59

ICO

-0.58

Champ

-0.57

POSITIVE LOGITS

 accordance

1.26

 relation

1.20

escap

1.19

 regards

1.19

 conjunction

1.15

 lieu

1.15

clus

1.14

 situ

1.11

 spite

1.10

effic

1.08

Activations Density 0.508%

locations or settings within a sentence

prepositions and their occurrences in various contexts

No Comments

No Known Activations