INDEX

Explanations

search terms related to Google and online searching

oai_token-act-pair · gpt-3.5-turbo

terms related to Google and its associated services or functionalities

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

»Ĵ

-0.64

channelAvailability

-0.64

Compar

-0.64

ashtra

-0.64

avorite

-0.63

ection

-0.63

Spring

-0.63

Joshua

-0.62

PORT

-0.62

 COUR

-0.62

POSITIVE LOGITS

uld

0.75

lers

0.75

 unnoticed

0.68

erman

0.67

warm

0.67

vernment

0.64

Zar

0.63

onz

0.63

fleet

0.63

Jew

0.63

Activations Density 0.052%

search terms related to Google and online searching

terms related to Google and its associated services or functionalities

No Comments

No Known Activations