INDEX

Explanations

verbs indicating future actions or possibilities

oai_token-act-pair · gpt-3.5-turbo

the end of a text segment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Seym

-0.72

 Niet

-0.71

 Azerb

-0.67

 Vaugh

-0.64

stood

-0.64

edIn

-0.63

accompan

-0.63

é¾

-0.62

Gaw

-0.60

Reason

-0.59

POSITIVE LOGITS

zbollah

0.62

actionDate

0.60

].

0.58

Psy

0.58

atem

0.57

];

0.57

llular

0.56

§

0.56

CRIPTION

0.55

Activations Density 0.100%

verbs indicating future actions or possibilities

the end of a text segment

No Comments

No Known Activations