INDEX

Explanations

specific entities or facts

oai_token-act-pair · gpt-3.5-turbo

various verbs or actions that are significant in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

verbs

-0.45

talk

-0.45

 Barkley

-0.44

 Engineers

-0.44

 Ukip

-0.42

zai

-0.42

 Cards

-0.42

Kee

-0.41

 Indie

-0.41

Ki

-0.41

POSITIVE LOGITS

ufact

0.63

uled

0.56

Nap

0.55

arius

0.54

heimer

0.54

leep

0.54

verage

0.53

anche

0.53

entially

0.53

ouble

0.52

Activations Density 1.509%

specific entities or facts

various verbs or actions that are significant in context

No Comments

No Known Activations