INDEX

Explanations

terms related to creativity or creative processes

oai_token-act-pair · gpt-3.5-turbo

terms related to creativity and creative expression

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

HEAD

-0.80

 Waterloo

-0.73

 Typhoon

-0.69

MER

-0.65

 Mandatory

-0.65

 Buffett

-0.64

 Doctrine

-0.63

phia

-0.63

 Ticket

-0.62

 Neighbor

-0.61

POSITIVE LOGITS

ivity

1.37

icles

1.10

icle

1.07

ivist

1.06

ors

1.04

ivities

1.01

es

0.98

ifact

0.98

ive

0.97

ives

0.96

Activations Density 0.019%

terms related to creativity or creative processes

terms related to creativity and creative expression

No Comments

No Known Activations