INDEX

Explanations

references to specific characters or names

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

 laureate

-0.63

FACE

-0.62

weight

-0.62

 poppy

-0.61

 Winchester

-0.60

oire

-0.60

 Tempest

-0.59

FORMATION

-0.59

 dividend

-0.59

ORGE

-0.58

POSITIVE LOGITS

umar

1.31

unin

1.28

ansas

1.24

ernel

1.21

nown

1.18

rish

1.17

htar

1.08

ileaks

1.06

owski

1.04

arak

1.03

Activations Density 0.672%

references to specific characters or names

No Comments

No Known Activations