INDEX

Explanations

proper names or technical terms related to various fields

oai_token-act-pair · gpt-3.5-turbo

proper nouns related to specific individuals or names

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

 corrid

-0.69

icter

-0.67

vertisement

-0.63

 cumbers

-0.58

mbuds

-0.56

 challeng

-0.56

 unden

-0.54

abolic

-0.53

 earthqu

-0.53

 reluct

-0.52

POSITIVE LOGITS

Â®

0.56

âĢİ

0.56

LLP

0.54

âĦ¢

0.53

ensis

0.51

aii

0.50

 Tyrann

0.49

 Parish

0.48

 Pres

0.47

Sr

0.47

Activations Density 0.573%

proper names or technical terms related to various fields

proper nouns related to specific individuals or names

No Comments

No Known Activations