INDEX

Explanations

references to the term "Canon" in various contexts, such as technology, literature, and culture

oai_token-act-pair · gpt-3.5-turbo

terms related to "canon" and its variations in various contexts

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

 Pupp

-0.69

-+

-0.68

stract

-0.67

Frameworks

-0.66

Sov

-0.65

RANT

-0.64

sie

-0.63

ELL

-0.63

Drug

-0.62

OOL

-0.61

POSITIVE LOGITS

icals

1.20

icles

1.16

ical

1.14

icle

0.97

icity

0.93

ique

0.88

nect

0.88

ically

0.87

structed

0.83

nery

0.83

Activations Density 0.020%

references to the term "Canon" in various contexts, such as technology, literature, and culture

terms related to "canon" and its variations in various contexts

No Comments

No Known Activations