INDEX

Explanations

titles or positions in a professional or formal context

oai_token-act-pair · gpt-3.5-turbo

titles and positions of authority within organizations

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

 unbeliev

-0.69

ayers

-0.61

enes

-0.60

lu

-0.60

 finer

-0.59

 vendors

-0.58

namese

-0.58

 expose

-0.58

 willingness

-0.58

irc

-0.57

POSITIVE LOGITS

ially

0.73

 emer

0.70

 overseeing

0.69

bernatorial

0.69

 Assist

0.67

Enh

0.61

 Protector

0.61

ragon

0.61

arte

0.61

 TAMADRA

0.60

Activations Density 0.195%

titles or positions in a professional or formal context

titles and positions of authority within organizations

No Comments

No Known Activations