INDEX

Explanations

descriptions of actions or functionalities related to products or services

oai_token-act-pair · gpt-3.5-turbo

phrases indicating necessity and potential outcomes

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

erenn

-0.67

hetti

-0.58

bledon

-0.57

ividual

-0.55

pherd

-0.55

ayson

-0.55

 Vaugh

-0.54

ograp

-0.53

Category

-0.51

ilaterally

-0.51

POSITIVE LOGITS

\":

0.54

 GDDR

0.53

 Malays

0.52

auna

0.51

azes

0.51

ratom

0.51

 Hulk

0.50

 Tradable

0.50

UTERS

0.49

ihad

0.48

Activations Density 0.238%

descriptions of actions or functionalities related to products or services

phrases indicating necessity and potential outcomes

No Comments

No Known Activations