INDEX

Explanations

the word 'Che' at various locations within the text

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_fs3072-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

3,072

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

Not in Any Lists

No Comments

Negative Logits

inally

-0.68

iate

-0.64

iating

-0.62

 Nadu

-0.62

inate

-0.62

inating

-0.61

 executive

-0.59

orph

-0.59

osite

-0.58

 Devils

-0.58

POSITIVE LOGITS

apeake

1.03

lde

1.03

tto

1.00

esy

0.99

cks

0.98

rote

0.97

tti

0.96

ppo

0.96

xp

0.95

tt

0.93

Activations Density 0.776%

the word 'Che' at various locations within the text

No Comments

No Known Activations