INDEX

Explanations

the word "How" at the beginning of sentences

oai_token-act-pair · gpt-3.5-turbo 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

•How

question

No Comments

Negative Logits

goers

-0.64

ptions

-0.62

ultimate

-0.62

 Feld

-0.61

outer

-0.58

article

-0.57

 hereafter

-0.56

piece

-0.56

room

-0.56

 Roller

-0.55

POSITIVE LOGITS

soever

1.17

ever

1.13

ells

1.04

beit

1.03

ling

0.93

itzer

0.87

dy

0.83

ls

0.82

 much

0.79

leep

0.79

Activations Density 0.063%

the word "How" at the beginning of sentences

No Comments

No Known Activations