INDEX

Explanations

instances of specific words starting with 'w'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Lumpur

-0.77

 culp

-0.66

uate

-0.66

 disclosing

-0.64

 anonymity

-0.63

 unpre

-0.63

 fracturing

-0.63

 headache

-0.62

 responsibility

-0.61

 Entered

-0.61

POSITIVE LOGITS

iggle

1.31

ither

1.26

affles

1.24

affle

1.23

ithering

1.18

icket

1.17

atts

1.16

atson

1.15

alt

1.13

ickets

1.13

Activations Density 0.016%

instances of specific words starting with 'w'

No Comments

No Known Activations