INDEX

Explanations

book and movie titles

oai_token-act-pair · gpt-3.5-turbo

keywords related to literary works

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ..."

-0.57

SPONSORED

-0.54

 è£ı

-0.52

 respectively

-0.48

 âĢ¦"

-0.48

 thereof

-0.47

 thereto

-0.47

EVs

-0.46

...

-0.45

Magikarp

-0.44

POSITIVE LOGITS

 Profile

0.60

sonian

0.59

xtap

0.54

emonium

0.51

theless

0.51

xiety

0.51

udos

0.50

intendent

0.49

anyahu

0.49

 Explan

0.49

Activations Density 0.621%

book and movie titles

keywords related to literary works

No Comments

No Known Activations