INDEX

Explanations

references to proper names or titles

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

ĸļ

-0.64

 derail

-0.64

 retrospect

-0.62

 facult

-0.61

 compr

-0.61

htt

-0.61

 Exile

-0.60

 craw

-0.59

oÄŁ

-0.58

nsics

-0.58

POSITIVE LOGITS

reetings

1.27

ourmet

1.25

oliath

1.25

ossip

1.24

opher

1.16

ospels

1.16

irlfriend

1.14

ambling

1.12

roups

1.12

ilded

1.11

Activations Density 0.320%

references to proper names or titles

No Comments

No Known Activations