INDEX

Explanations

keywords related to popular TV shows and video games

oai_token-act-pair · gpt-3.5-turbo

titles and series names associated with popular media

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

housing

-0.70

efe

-0.70

private

-0.67

¿½

-0.66

 VIEW

-0.65

prus

-0.65

ESSION

-0.64

ession

-0.64

aye

-0.64

mand

-0.64

POSITIVE LOGITS

 sequels

0.97

 trilogy

0.84

 fandom

0.81

 films

0.81

 sequel

0.80

 Characters

0.79

 Animated

0.78

 arcs

0.77

 franchises

0.77

 trope

0.76

Activations Density 0.041%

keywords related to popular TV shows and video games

titles and series names associated with popular media

No Comments

No Known Activations