INDEX

Explanations

phrases related to the plot or narrative of a story or production

oai_token-act-pair · gpt-3.5-turbo

references to storylines in various narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

uters

-0.89

ateurs

-0.88

ury

-0.81

cler

-0.79

essee

-0.78

prus

-0.77

achev

-0.77

itudes

-0.76

ensation

-0.75

berman

-0.73

POSITIVE LOGITS

 storylines

0.88

 arcs

0.87

TextColor

0.81

 storyline

0.80

SourceFile

0.74

arc

0.72

 backstory

0.70

 Twist

0.70

 conclud

0.70

 revolving

0.69

Activations Density 0.016%

phrases related to the plot or narrative of a story or production

references to storylines in various narratives

No Comments

No Known Activations