INDEX

Explanations

terms related to specific fields or industries

oai_token-act-pair · gpt-3.5-turbo

keywords related to various societal and health issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.53

 Katy

-0.52

ETA

-0.51

ADVERTISEMENT

-0.51

 Diet

-0.51

advertising

-0.50

 unse

-0.49

abba

-0.49

âĢİ

-0.49

 Ridley

-0.49

POSITIVE LOGITS

 lovers

0.61

 drinkers

0.58

 interventions

0.57

 suppliers

0.57

 accounted

0.56

 specialists

0.56

 differe

0.56

 historians

0.55

 enthusiasts

0.54

 coordin

0.53

Activations Density 0.906%

terms related to specific fields or industries

keywords related to various societal and health issues

No Comments

No Known Activations