INDEX

Explanations

words related to the act of portraying or depicting something

oai_token-act-pair · gpt-3.5-turbo

the term "portray" and its variations in relation to representation and depiction

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

foreseen

-0.77

duct

-0.74

doms

-0.71

zyme

-0.70

andr

-0.68

anwhile

-0.67

wegian

-0.66

waters

-0.64

speak

-0.64

sterdam

-0.64

POSITIVE LOGITS

 portray

1.12

 depictions

1.10

 portrayal

1.05

 portrays

1.05

 portraying

0.95

 depiction

0.92

 depicting

0.88

 portrayed

0.85

ãĤ¨ãĥ«

0.85

 depict

0.84

Activations Density 0.040%

words related to the act of portraying or depicting something

the term "portray" and its variations in relation to representation and depiction

No Comments

No Known Activations