INDEX

Explanations

words related to aspirations, desires, and ambitions

oai_token-act-pair · gpt-3.5-turbo

references to dreams and aspirations

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

avis

-0.80

idges

-0.70

oute

-0.69

andise

-0.67

ãĥĺãĥ©

-0.67

 ease

-0.66

 wrinkles

-0.65

anti

-0.64

ahon

-0.64

 tabl

-0.64

POSITIVE LOGITS

tek

0.98

scape

0.95

 dreaming

0.91

 dream

0.87

dream

0.85

 dreams

0.84

liner

0.79

Hack

0.77

Dream

0.77

hack

0.76

Activations Density 0.019%

words related to aspirations, desires, and ambitions

references to dreams and aspirations

No Comments

No Known Activations