INDEX

Explanations

specific terms related to video games and gameplay, like game locations, items, and actions

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

UNCH

-0.73

ELF

-0.63

ASED

-0.63

ctor

-0.61

ARP

-0.61

ICT

-0.61

astern

-0.61

XT

-0.60

CE

-0.60

IRO

-0.59

POSITIVE LOGITS

2.85

sburg

1.71

sie

1.58

sis

1.46

sb

1.46

sburgh

1.42

ski

1.39

sg

1.37

sf

1.34

sch

1.33

Activations Density 2.398%

specific terms related to video games and gameplay, like game locations, items, and actions

No Comments

No Known Activations