INDEX

Explanations

phrases related to unity or coming together as a group

oai_token-act-pair · gpt-3.5-turbo

expressions of unity and collaboration within a community

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

cock

-0.67

den

-0.64

ako

-0.62

dark

-0.62

outer

-0.60

qus

-0.58

 slit

-0.58

ocalypse

-0.58

^{

-0.57

outine

-0.57

POSITIVE LOGITS

arity

0.77

DragonMagazine

0.70

halla

0.69

unity

0.69

 seamlessly

0.68

puff

0.67

essional

0.67

iliation

0.65

ÃįÃį

0.65

displayText

0.64

Activations Density 0.024%

phrases related to unity or coming together as a group

expressions of unity and collaboration within a community

No Comments

No Known Activations